[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-trail-of-bits-pr-improver":3,"mdc--y7imeh-key":38,"related-org-trail-of-bits-pr-improver":1026,"related-repo-trail-of-bits-pr-improver":1186},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":33,"sourceUrl":36,"mdContent":37},"pr-improver","automate pull request review and fixes","Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directories the branch touched. Reviews are performed by an installed PR-review skill (default: pr-review-toolkit's review-pr). Use to fix review findings on a branch before opening or updating a pull request ('clean up this branch', 'fix this PR until review passes', 'run review-and-fix on my changes'). NOT for a one-time review — run the PR-review skill directly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"trail-of-bits","Trail of Bits","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Ftrail-of-bits.png","trailofbits",[13,17,20,23],{"name":14,"slug":15,"type":16},"Automation","automation","tag",{"name":18,"slug":19,"type":16},"Code Review","code-review",{"name":21,"slug":22,"type":16},"Engineering","engineering",{"name":24,"slug":25,"type":16},"Pull Requests","pull-requests",6139,"https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills","2026-08-27T13:31:52.475697",null,541,[32],"agent-skills",{"repoUrl":27,"stars":26,"forks":30,"topics":34,"description":35},[32],"Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows","https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills\u002Ftree\u002FHEAD\u002Fplugins\u002Fcode-improver\u002Fskills\u002Fpr-improver","---\nname: pr-improver\ndescription: \"Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directories the branch touched. Reviews are performed by an installed PR-review skill (default: pr-review-toolkit's review-pr). Use to fix review findings on a branch before opening or updating a pull request ('clean up this branch', 'fix this PR until review passes', 'run review-and-fix on my changes'). NOT for a one-time review — run the PR-review skill directly.\"\nargument-hint: \"[BASE_BRANCH] [--reviewer \u003Cskill-or-agent>] [--max-rounds N]\"\nallowed-tools: Bash Glob Read TaskOutput TaskStop Workflow\n---\n\n# PR Improver\n\nImprove the current branch by running `\u002Fcode-improver:improve` — a dynamic workflow that\nloops a PR reviewer and a fixer subagent over the branch's changes until a review\nreports zero critical\u002Fmajor findings. The loop, its ledger, and its guards live in the\nworkflow; this skill derives the scope from the branch diff and relays the outcome.\n\n## Starting the loop\n\nThe user provided: `$ARGUMENTS` (if empty, take base branch and preferences from the\nconversation).\n\n### 1. Resolve the branch and its change surface\n\n1. Repo root: `git rev-parse --show-toplevel`. Fail loudly outside a repository.\n2. Base: the argument if given, else the repository's default branch\n   (`git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD` → its short name, falling back to\n   `main`). Refuse to run when the current branch IS the base — there is no diff to\n   improve.\n3. Changed files: `git diff --name-only \u003Cbase>...HEAD`. If empty, say so and stop.\n4. Scope: the changed files' **directories**, widened — per-file globs are too tight\n   (PR fixes legitimately add tests next to changed code). Map each changed file to its\n   repo-relative directory glob `\u003Cdir>\u002F**` (`**` at the repo root only if files at the\n   root changed), then deduplicate and drop globs covered by another.\n\n### 2. Resolve the loop script\n\nThe loop is the dynamic workflow `workflows\u002Fimprove.js` in this plugin. Launch it by\npath: `scriptPath` takes a resolved absolute path, and the Workflow tool's `name` resolves\nbuilt-in and project workflows, so a marketplace-installed one may not answer to\n`code-improver:improve`. Try in order, first hit wins — the home directories come before\n`.` so an installed copy beats a checkout of this marketplace:\n\n1. `Bash: ls -d -- \"${CLAUDE_PLUGIN_ROOT}\u002Fworkflows\u002Fimprove.js\"`\n2. `Bash: ls -d -- \"${CODEX_PLUGIN_ROOT}\u002Fworkflows\u002Fimprove.js\"` (if that variable is set instead)\n3. `Bash: find ~\u002F.claude ~\u002F.codex . -maxdepth 7 -path '*\u002Fcode-improver\u002Fworkflows\u002Fimprove.js' -print -quit 2>\u002Fdev\u002Fnull`\n\nUse the path exactly as printed. Its plugin directory — the path with\n`\u002Fworkflows\u002Fimprove.js` removed — is `pluginRoot`. If all three come back empty, try\n`{name: \"code-improver:improve\"}` once; if that is unavailable too, stop and say the loop\ncould not be located. Do not assemble a path by hand and do not improvise the loop.\n\n### 3. Invoke the workflow\n\nRun it with the Workflow tool, `{scriptPath: \"\u003Cthe path from step 2>\", args: {...}}`:\n\n```json\n{\n  \"target\": \"\u003Crepo root>\",\n  \"reviewer\": {\n    \"kind\": \"skill\",\n    \"name\": \"pr-review-toolkit:review-pr\",\n    \"notes\": \"Review the working tree's changes against \u003Cbase> as a pull request: correctness, tests, error handling, and the review dimensions the skill prescribes.\"\n  },\n  \"scope\": [\"\u003Cderived-dir-glob>\u002F**\"],\n  \"pluginRoot\": \"\u003Cthe plugin directory from step 2>\",\n  \"maxRounds\": 5\n}\n```\n\n- `reviewer` — the default above requires the `pr-review-toolkit` plugin. When the user\n  names a different PR reviewer (skill or agent), use it, with kind set accordingly.\n- `maxRounds` only if the user asked for a different cap.\n- `pluginRoot` lets the run find its metrics collector; omit the key only if step 2 fell\n  through to the workflow name — the workflow then searches for itself.\n- `finalize` defaults are right for PRs: no version bump unless the branch sits inside a\n  plugin, narration strip and docs pass on.\n- `decision` only on continuation (below).\n\nThe loop's baseline snapshot is the tree at loop start — its scope guard protects the\nbranch's uncommitted work; the PR's own commits are what the reviewer reviews.\n\nThe workflow runs in the background and needs no babysitting: it reviews, fixes,\nre-reviews, checks scope after every fix round, and can only complete on a clean review.\nIt never commits; all changes stay in the working tree.\n\n**If the Workflow tool is unavailable or denied, stop and say so.** Do not improvise the\nloop inline with direct edits — the ledger, scope guard, and escalation guarantees live\nin the workflow, and an inline imitation has none of them.\n\n**If the result is `halted: \"reviewer-unavailable\"`, relay it and stop.** The reviewer\nis not installed in this session; tell the user which plugin provides it (the default\nneeds `pr-review-toolkit`) and re-run after installing. Do not review the branch\nyourself.\n\n**Do not end your turn while the loop is running.** The Workflow tool returns a task id\nimmediately; the result comes later. In an interactive session the completion\nnotification re-invokes you — wait for it. In a non-interactive run (scripted, CI, eval)\nthere is no later turn: stopping abandons the loop mid-round, so after launching, poll\nthe task (TaskOutput with the returned task id, or sleep-and-recheck) until it completes,\nthen relay the result. A session that answers \"the loop is running, I'll report later\"\nhas lost the run.\n\n## Relaying the result\n\nThe workflow returns a structured result. Report it honestly — the distinctions matter:\n\n- **`converged: true`** — the last action was a review with zero critical\u002Fmajor findings.\n  Report rounds used, remaining minor findings (`open_minor_count`), and the artifact\n  paths (`ledger_path`, `metrics`).\n- **`capped: true`** — the fix budget ran out and the FINAL review still found blocking\n  issues. Say plainly: **capped, NOT converged**, and list `open_blocking`. Do not\n  present this as success.\n- **`escalation`** — the loop detected it was not converging (recurring findings,\n  non-decreasing counts, or a fix relocating a problem). Relay the escalation message and\n  finding ids to the user: this needs a design decision, not more rounds.\n- **`halted`** — a guard fired (scope violation, unregistered new files, a dead or\n  unavailable reviewer, or a finalize pass whose own edits failed the check that follows\n  it). Relay the paths in `violations`\u002F`new_untracked_files`, the sites in\n  `finalize_regressions`, and the notes.\n- **`notes`** always travel with the result — surface them; they include loud warnings\n  such as \"a git repository was initialized\".\n\n## Continuing after an escalation\n\nThe loop stops on escalation by design. When the user decides, start a fresh run with\nthe same args plus:\n\n```json\n{ \"decision\": \"\u003Cthe user's ruling, verbatim>\" }\n```\n\nThe new run reloads the on-disk ledger, so every finding, rejection, and verdict carries\nover — rounds restart, re-derivation does not.\n\nTo stop a running loop, stop the workflow task (TaskStop); the ledger on disk is current\nto the last round and a re-run resumes from it.\n\n## When NOT to use\n\n- **One-time review**: run the PR-review skill directly; the loop's value is iteration\n- **A skill**: use the `skill-improver` entry — it wires the right reviewer\n- **Unpushed exploratory work**: review-and-fix loops harden a diff; while the shape is\n  fluid, manual iteration gives more control\n",{"data":39,"body":42},{"name":4,"description":6,"argument-hint":40,"allowed-tools":41},"[BASE_BRANCH] [--reviewer \u003Cskill-or-agent>] [--max-rounds N]","Bash Glob Read TaskOutput TaskStop Workflow",{"type":43,"children":44},"root",[45,53,68,75,88,95,176,182,227,259,288,294,307,638,702,707,712,722,747,757,763,768,903,909,914,963,968,973,979,1020],{"type":46,"tag":47,"props":48,"children":49},"element","h1",{"id":4},[50],{"type":51,"value":52},"text","PR Improver",{"type":46,"tag":54,"props":55,"children":56},"p",{},[57,59,66],{"type":51,"value":58},"Improve the current branch by running ",{"type":46,"tag":60,"props":61,"children":63},"code",{"className":62},[],[64],{"type":51,"value":65},"\u002Fcode-improver:improve",{"type":51,"value":67}," — a dynamic workflow that\nloops a PR reviewer and a fixer subagent over the branch's changes until a review\nreports zero critical\u002Fmajor findings. The loop, its ledger, and its guards live in the\nworkflow; this skill derives the scope from the branch diff and relays the outcome.",{"type":46,"tag":69,"props":70,"children":72},"h2",{"id":71},"starting-the-loop",[73],{"type":51,"value":74},"Starting the loop",{"type":46,"tag":54,"props":76,"children":77},{},[78,80,86],{"type":51,"value":79},"The user provided: ",{"type":46,"tag":60,"props":81,"children":83},{"className":82},[],[84],{"type":51,"value":85},"$ARGUMENTS",{"type":51,"value":87}," (if empty, take base branch and preferences from the\nconversation).",{"type":46,"tag":89,"props":90,"children":92},"h3",{"id":91},"_1-resolve-the-branch-and-its-change-surface",[93],{"type":51,"value":94},"1. Resolve the branch and its change surface",{"type":46,"tag":96,"props":97,"children":98},"ol",{},[99,113,134,147],{"type":46,"tag":100,"props":101,"children":102},"li",{},[103,105,111],{"type":51,"value":104},"Repo root: ",{"type":46,"tag":60,"props":106,"children":108},{"className":107},[],[109],{"type":51,"value":110},"git rev-parse --show-toplevel",{"type":51,"value":112},". Fail loudly outside a repository.",{"type":46,"tag":100,"props":114,"children":115},{},[116,118,124,126,132],{"type":51,"value":117},"Base: the argument if given, else the repository's default branch\n(",{"type":46,"tag":60,"props":119,"children":121},{"className":120},[],[122],{"type":51,"value":123},"git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD",{"type":51,"value":125}," → its short name, falling back to\n",{"type":46,"tag":60,"props":127,"children":129},{"className":128},[],[130],{"type":51,"value":131},"main",{"type":51,"value":133},"). Refuse to run when the current branch IS the base — there is no diff to\nimprove.",{"type":46,"tag":100,"props":135,"children":136},{},[137,139,145],{"type":51,"value":138},"Changed files: ",{"type":46,"tag":60,"props":140,"children":142},{"className":141},[],[143],{"type":51,"value":144},"git diff --name-only \u003Cbase>...HEAD",{"type":51,"value":146},". If empty, say so and stop.",{"type":46,"tag":100,"props":148,"children":149},{},[150,152,158,160,166,168,174],{"type":51,"value":151},"Scope: the changed files' ",{"type":46,"tag":153,"props":154,"children":155},"strong",{},[156],{"type":51,"value":157},"directories",{"type":51,"value":159},", widened — per-file globs are too tight\n(PR fixes legitimately add tests next to changed code). Map each changed file to its\nrepo-relative directory glob ",{"type":46,"tag":60,"props":161,"children":163},{"className":162},[],[164],{"type":51,"value":165},"\u003Cdir>\u002F**",{"type":51,"value":167}," (",{"type":46,"tag":60,"props":169,"children":171},{"className":170},[],[172],{"type":51,"value":173},"**",{"type":51,"value":175}," at the repo root only if files at the\nroot changed), then deduplicate and drop globs covered by another.",{"type":46,"tag":89,"props":177,"children":179},{"id":178},"_2-resolve-the-loop-script",[180],{"type":51,"value":181},"2. Resolve the loop script",{"type":46,"tag":54,"props":183,"children":184},{},[185,187,193,195,201,203,209,211,217,219,225],{"type":51,"value":186},"The loop is the dynamic workflow ",{"type":46,"tag":60,"props":188,"children":190},{"className":189},[],[191],{"type":51,"value":192},"workflows\u002Fimprove.js",{"type":51,"value":194}," in this plugin. Launch it by\npath: ",{"type":46,"tag":60,"props":196,"children":198},{"className":197},[],[199],{"type":51,"value":200},"scriptPath",{"type":51,"value":202}," takes a resolved absolute path, and the Workflow tool's ",{"type":46,"tag":60,"props":204,"children":206},{"className":205},[],[207],{"type":51,"value":208},"name",{"type":51,"value":210}," resolves\nbuilt-in and project workflows, so a marketplace-installed one may not answer to\n",{"type":46,"tag":60,"props":212,"children":214},{"className":213},[],[215],{"type":51,"value":216},"code-improver:improve",{"type":51,"value":218},". Try in order, first hit wins — the home directories come before\n",{"type":46,"tag":60,"props":220,"children":222},{"className":221},[],[223],{"type":51,"value":224},".",{"type":51,"value":226}," so an installed copy beats a checkout of this marketplace:",{"type":46,"tag":96,"props":228,"children":229},{},[230,239,250],{"type":46,"tag":100,"props":231,"children":232},{},[233],{"type":46,"tag":60,"props":234,"children":236},{"className":235},[],[237],{"type":51,"value":238},"Bash: ls -d -- \"${CLAUDE_PLUGIN_ROOT}\u002Fworkflows\u002Fimprove.js\"",{"type":46,"tag":100,"props":240,"children":241},{},[242,248],{"type":46,"tag":60,"props":243,"children":245},{"className":244},[],[246],{"type":51,"value":247},"Bash: ls -d -- \"${CODEX_PLUGIN_ROOT}\u002Fworkflows\u002Fimprove.js\"",{"type":51,"value":249}," (if that variable is set instead)",{"type":46,"tag":100,"props":251,"children":252},{},[253],{"type":46,"tag":60,"props":254,"children":256},{"className":255},[],[257],{"type":51,"value":258},"Bash: find ~\u002F.claude ~\u002F.codex . -maxdepth 7 -path '*\u002Fcode-improver\u002Fworkflows\u002Fimprove.js' -print -quit 2>\u002Fdev\u002Fnull",{"type":46,"tag":54,"props":260,"children":261},{},[262,264,270,272,278,280,286],{"type":51,"value":263},"Use the path exactly as printed. Its plugin directory — the path with\n",{"type":46,"tag":60,"props":265,"children":267},{"className":266},[],[268],{"type":51,"value":269},"\u002Fworkflows\u002Fimprove.js",{"type":51,"value":271}," removed — is ",{"type":46,"tag":60,"props":273,"children":275},{"className":274},[],[276],{"type":51,"value":277},"pluginRoot",{"type":51,"value":279},". If all three come back empty, try\n",{"type":46,"tag":60,"props":281,"children":283},{"className":282},[],[284],{"type":51,"value":285},"{name: \"code-improver:improve\"}",{"type":51,"value":287}," once; if that is unavailable too, stop and say the loop\ncould not be located. Do not assemble a path by hand and do not improvise the loop.",{"type":46,"tag":89,"props":289,"children":291},{"id":290},"_3-invoke-the-workflow",[292],{"type":51,"value":293},"3. Invoke the workflow",{"type":46,"tag":54,"props":295,"children":296},{},[297,299,305],{"type":51,"value":298},"Run it with the Workflow tool, ",{"type":46,"tag":60,"props":300,"children":302},{"className":301},[],[303],{"type":51,"value":304},"{scriptPath: \"\u003Cthe path from step 2>\", args: {...}}",{"type":51,"value":306},":",{"type":46,"tag":308,"props":309,"children":314},"pre",{"className":310,"code":311,"language":312,"meta":313,"style":313},"language-json shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","{\n  \"target\": \"\u003Crepo root>\",\n  \"reviewer\": {\n    \"kind\": \"skill\",\n    \"name\": \"pr-review-toolkit:review-pr\",\n    \"notes\": \"Review the working tree's changes against \u003Cbase> as a pull request: correctness, tests, error handling, and the review dimensions the skill prescribes.\"\n  },\n  \"scope\": [\"\u003Cderived-dir-glob>\u002F**\"],\n  \"pluginRoot\": \"\u003Cthe plugin directory from step 2>\",\n  \"maxRounds\": 5\n}\n","json","",[315],{"type":46,"tag":60,"props":316,"children":317},{"__ignoreMap":313},[318,330,374,400,440,477,512,521,565,602,629],{"type":46,"tag":319,"props":320,"children":323},"span",{"class":321,"line":322},"line",1,[324],{"type":46,"tag":319,"props":325,"children":327},{"style":326},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[328],{"type":51,"value":329},"{\n",{"type":46,"tag":319,"props":331,"children":333},{"class":321,"line":332},2,[334,339,345,350,354,359,365,369],{"type":46,"tag":319,"props":335,"children":336},{"style":326},[337],{"type":51,"value":338},"  \"",{"type":46,"tag":319,"props":340,"children":342},{"style":341},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[343],{"type":51,"value":344},"target",{"type":46,"tag":319,"props":346,"children":347},{"style":326},[348],{"type":51,"value":349},"\"",{"type":46,"tag":319,"props":351,"children":352},{"style":326},[353],{"type":51,"value":306},{"type":46,"tag":319,"props":355,"children":356},{"style":326},[357],{"type":51,"value":358}," \"",{"type":46,"tag":319,"props":360,"children":362},{"style":361},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[363],{"type":51,"value":364},"\u003Crepo root>",{"type":46,"tag":319,"props":366,"children":367},{"style":326},[368],{"type":51,"value":349},{"type":46,"tag":319,"props":370,"children":371},{"style":326},[372],{"type":51,"value":373},",\n",{"type":46,"tag":319,"props":375,"children":377},{"class":321,"line":376},3,[378,382,387,391,395],{"type":46,"tag":319,"props":379,"children":380},{"style":326},[381],{"type":51,"value":338},{"type":46,"tag":319,"props":383,"children":384},{"style":341},[385],{"type":51,"value":386},"reviewer",{"type":46,"tag":319,"props":388,"children":389},{"style":326},[390],{"type":51,"value":349},{"type":46,"tag":319,"props":392,"children":393},{"style":326},[394],{"type":51,"value":306},{"type":46,"tag":319,"props":396,"children":397},{"style":326},[398],{"type":51,"value":399}," {\n",{"type":46,"tag":319,"props":401,"children":403},{"class":321,"line":402},4,[404,409,415,419,423,427,432,436],{"type":46,"tag":319,"props":405,"children":406},{"style":326},[407],{"type":51,"value":408},"    \"",{"type":46,"tag":319,"props":410,"children":412},{"style":411},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[413],{"type":51,"value":414},"kind",{"type":46,"tag":319,"props":416,"children":417},{"style":326},[418],{"type":51,"value":349},{"type":46,"tag":319,"props":420,"children":421},{"style":326},[422],{"type":51,"value":306},{"type":46,"tag":319,"props":424,"children":425},{"style":326},[426],{"type":51,"value":358},{"type":46,"tag":319,"props":428,"children":429},{"style":361},[430],{"type":51,"value":431},"skill",{"type":46,"tag":319,"props":433,"children":434},{"style":326},[435],{"type":51,"value":349},{"type":46,"tag":319,"props":437,"children":438},{"style":326},[439],{"type":51,"value":373},{"type":46,"tag":319,"props":441,"children":443},{"class":321,"line":442},5,[444,448,452,456,460,464,469,473],{"type":46,"tag":319,"props":445,"children":446},{"style":326},[447],{"type":51,"value":408},{"type":46,"tag":319,"props":449,"children":450},{"style":411},[451],{"type":51,"value":208},{"type":46,"tag":319,"props":453,"children":454},{"style":326},[455],{"type":51,"value":349},{"type":46,"tag":319,"props":457,"children":458},{"style":326},[459],{"type":51,"value":306},{"type":46,"tag":319,"props":461,"children":462},{"style":326},[463],{"type":51,"value":358},{"type":46,"tag":319,"props":465,"children":466},{"style":361},[467],{"type":51,"value":468},"pr-review-toolkit:review-pr",{"type":46,"tag":319,"props":470,"children":471},{"style":326},[472],{"type":51,"value":349},{"type":46,"tag":319,"props":474,"children":475},{"style":326},[476],{"type":51,"value":373},{"type":46,"tag":319,"props":478,"children":480},{"class":321,"line":479},6,[481,485,490,494,498,502,507],{"type":46,"tag":319,"props":482,"children":483},{"style":326},[484],{"type":51,"value":408},{"type":46,"tag":319,"props":486,"children":487},{"style":411},[488],{"type":51,"value":489},"notes",{"type":46,"tag":319,"props":491,"children":492},{"style":326},[493],{"type":51,"value":349},{"type":46,"tag":319,"props":495,"children":496},{"style":326},[497],{"type":51,"value":306},{"type":46,"tag":319,"props":499,"children":500},{"style":326},[501],{"type":51,"value":358},{"type":46,"tag":319,"props":503,"children":504},{"style":361},[505],{"type":51,"value":506},"Review the working tree's changes against \u003Cbase> as a pull request: correctness, tests, error handling, and the review dimensions the skill prescribes.",{"type":46,"tag":319,"props":508,"children":509},{"style":326},[510],{"type":51,"value":511},"\"\n",{"type":46,"tag":319,"props":513,"children":515},{"class":321,"line":514},7,[516],{"type":46,"tag":319,"props":517,"children":518},{"style":326},[519],{"type":51,"value":520},"  },\n",{"type":46,"tag":319,"props":522,"children":524},{"class":321,"line":523},8,[525,529,534,538,542,547,551,556,560],{"type":46,"tag":319,"props":526,"children":527},{"style":326},[528],{"type":51,"value":338},{"type":46,"tag":319,"props":530,"children":531},{"style":341},[532],{"type":51,"value":533},"scope",{"type":46,"tag":319,"props":535,"children":536},{"style":326},[537],{"type":51,"value":349},{"type":46,"tag":319,"props":539,"children":540},{"style":326},[541],{"type":51,"value":306},{"type":46,"tag":319,"props":543,"children":544},{"style":326},[545],{"type":51,"value":546}," [",{"type":46,"tag":319,"props":548,"children":549},{"style":326},[550],{"type":51,"value":349},{"type":46,"tag":319,"props":552,"children":553},{"style":361},[554],{"type":51,"value":555},"\u003Cderived-dir-glob>\u002F**",{"type":46,"tag":319,"props":557,"children":558},{"style":326},[559],{"type":51,"value":349},{"type":46,"tag":319,"props":561,"children":562},{"style":326},[563],{"type":51,"value":564},"],\n",{"type":46,"tag":319,"props":566,"children":568},{"class":321,"line":567},9,[569,573,577,581,585,589,594,598],{"type":46,"tag":319,"props":570,"children":571},{"style":326},[572],{"type":51,"value":338},{"type":46,"tag":319,"props":574,"children":575},{"style":341},[576],{"type":51,"value":277},{"type":46,"tag":319,"props":578,"children":579},{"style":326},[580],{"type":51,"value":349},{"type":46,"tag":319,"props":582,"children":583},{"style":326},[584],{"type":51,"value":306},{"type":46,"tag":319,"props":586,"children":587},{"style":326},[588],{"type":51,"value":358},{"type":46,"tag":319,"props":590,"children":591},{"style":361},[592],{"type":51,"value":593},"\u003Cthe plugin directory from step 2>",{"type":46,"tag":319,"props":595,"children":596},{"style":326},[597],{"type":51,"value":349},{"type":46,"tag":319,"props":599,"children":600},{"style":326},[601],{"type":51,"value":373},{"type":46,"tag":319,"props":603,"children":605},{"class":321,"line":604},10,[606,610,615,619,623],{"type":46,"tag":319,"props":607,"children":608},{"style":326},[609],{"type":51,"value":338},{"type":46,"tag":319,"props":611,"children":612},{"style":341},[613],{"type":51,"value":614},"maxRounds",{"type":46,"tag":319,"props":616,"children":617},{"style":326},[618],{"type":51,"value":349},{"type":46,"tag":319,"props":620,"children":621},{"style":326},[622],{"type":51,"value":306},{"type":46,"tag":319,"props":624,"children":626},{"style":625},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[627],{"type":51,"value":628}," 5\n",{"type":46,"tag":319,"props":630,"children":632},{"class":321,"line":631},11,[633],{"type":46,"tag":319,"props":634,"children":635},{"style":326},[636],{"type":51,"value":637},"}\n",{"type":46,"tag":639,"props":640,"children":641},"ul",{},[642,660,670,680,691],{"type":46,"tag":100,"props":643,"children":644},{},[645,650,652,658],{"type":46,"tag":60,"props":646,"children":648},{"className":647},[],[649],{"type":51,"value":386},{"type":51,"value":651}," — the default above requires the ",{"type":46,"tag":60,"props":653,"children":655},{"className":654},[],[656],{"type":51,"value":657},"pr-review-toolkit",{"type":51,"value":659}," plugin. When the user\nnames a different PR reviewer (skill or agent), use it, with kind set accordingly.",{"type":46,"tag":100,"props":661,"children":662},{},[663,668],{"type":46,"tag":60,"props":664,"children":666},{"className":665},[],[667],{"type":51,"value":614},{"type":51,"value":669}," only if the user asked for a different cap.",{"type":46,"tag":100,"props":671,"children":672},{},[673,678],{"type":46,"tag":60,"props":674,"children":676},{"className":675},[],[677],{"type":51,"value":277},{"type":51,"value":679}," lets the run find its metrics collector; omit the key only if step 2 fell\nthrough to the workflow name — the workflow then searches for itself.",{"type":46,"tag":100,"props":681,"children":682},{},[683,689],{"type":46,"tag":60,"props":684,"children":686},{"className":685},[],[687],{"type":51,"value":688},"finalize",{"type":51,"value":690}," defaults are right for PRs: no version bump unless the branch sits inside a\nplugin, narration strip and docs pass on.",{"type":46,"tag":100,"props":692,"children":693},{},[694,700],{"type":46,"tag":60,"props":695,"children":697},{"className":696},[],[698],{"type":51,"value":699},"decision",{"type":51,"value":701}," only on continuation (below).",{"type":46,"tag":54,"props":703,"children":704},{},[705],{"type":51,"value":706},"The loop's baseline snapshot is the tree at loop start — its scope guard protects the\nbranch's uncommitted work; the PR's own commits are what the reviewer reviews.",{"type":46,"tag":54,"props":708,"children":709},{},[710],{"type":51,"value":711},"The workflow runs in the background and needs no babysitting: it reviews, fixes,\nre-reviews, checks scope after every fix round, and can only complete on a clean review.\nIt never commits; all changes stay in the working tree.",{"type":46,"tag":54,"props":713,"children":714},{},[715,720],{"type":46,"tag":153,"props":716,"children":717},{},[718],{"type":51,"value":719},"If the Workflow tool is unavailable or denied, stop and say so.",{"type":51,"value":721}," Do not improvise the\nloop inline with direct edits — the ledger, scope guard, and escalation guarantees live\nin the workflow, and an inline imitation has none of them.",{"type":46,"tag":54,"props":723,"children":724},{},[725,738,740,745],{"type":46,"tag":153,"props":726,"children":727},{},[728,730,736],{"type":51,"value":729},"If the result is ",{"type":46,"tag":60,"props":731,"children":733},{"className":732},[],[734],{"type":51,"value":735},"halted: \"reviewer-unavailable\"",{"type":51,"value":737},", relay it and stop.",{"type":51,"value":739}," The reviewer\nis not installed in this session; tell the user which plugin provides it (the default\nneeds ",{"type":46,"tag":60,"props":741,"children":743},{"className":742},[],[744],{"type":51,"value":657},{"type":51,"value":746},") and re-run after installing. Do not review the branch\nyourself.",{"type":46,"tag":54,"props":748,"children":749},{},[750,755],{"type":46,"tag":153,"props":751,"children":752},{},[753],{"type":51,"value":754},"Do not end your turn while the loop is running.",{"type":51,"value":756}," The Workflow tool returns a task id\nimmediately; the result comes later. In an interactive session the completion\nnotification re-invokes you — wait for it. In a non-interactive run (scripted, CI, eval)\nthere is no later turn: stopping abandons the loop mid-round, so after launching, poll\nthe task (TaskOutput with the returned task id, or sleep-and-recheck) until it completes,\nthen relay the result. A session that answers \"the loop is running, I'll report later\"\nhas lost the run.",{"type":46,"tag":69,"props":758,"children":760},{"id":759},"relaying-the-result",[761],{"type":51,"value":762},"Relaying the result",{"type":46,"tag":54,"props":764,"children":765},{},[766],{"type":51,"value":767},"The workflow returns a structured result. Report it honestly — the distinctions matter:",{"type":46,"tag":639,"props":769,"children":770},{},[771,809,838,852,890],{"type":46,"tag":100,"props":772,"children":773},{},[774,783,785,791,793,799,801,807],{"type":46,"tag":153,"props":775,"children":776},{},[777],{"type":46,"tag":60,"props":778,"children":780},{"className":779},[],[781],{"type":51,"value":782},"converged: true",{"type":51,"value":784}," — the last action was a review with zero critical\u002Fmajor findings.\nReport rounds used, remaining minor findings (",{"type":46,"tag":60,"props":786,"children":788},{"className":787},[],[789],{"type":51,"value":790},"open_minor_count",{"type":51,"value":792},"), and the artifact\npaths (",{"type":46,"tag":60,"props":794,"children":796},{"className":795},[],[797],{"type":51,"value":798},"ledger_path",{"type":51,"value":800},", ",{"type":46,"tag":60,"props":802,"children":804},{"className":803},[],[805],{"type":51,"value":806},"metrics",{"type":51,"value":808},").",{"type":46,"tag":100,"props":810,"children":811},{},[812,821,823,828,830,836],{"type":46,"tag":153,"props":813,"children":814},{},[815],{"type":46,"tag":60,"props":816,"children":818},{"className":817},[],[819],{"type":51,"value":820},"capped: true",{"type":51,"value":822}," — the fix budget ran out and the FINAL review still found blocking\nissues. Say plainly: ",{"type":46,"tag":153,"props":824,"children":825},{},[826],{"type":51,"value":827},"capped, NOT converged",{"type":51,"value":829},", and list ",{"type":46,"tag":60,"props":831,"children":833},{"className":832},[],[834],{"type":51,"value":835},"open_blocking",{"type":51,"value":837},". Do not\npresent this as success.",{"type":46,"tag":100,"props":839,"children":840},{},[841,850],{"type":46,"tag":153,"props":842,"children":843},{},[844],{"type":46,"tag":60,"props":845,"children":847},{"className":846},[],[848],{"type":51,"value":849},"escalation",{"type":51,"value":851}," — the loop detected it was not converging (recurring findings,\nnon-decreasing counts, or a fix relocating a problem). Relay the escalation message and\nfinding ids to the user: this needs a design decision, not more rounds.",{"type":46,"tag":100,"props":853,"children":854},{},[855,864,866,872,874,880,882,888],{"type":46,"tag":153,"props":856,"children":857},{},[858],{"type":46,"tag":60,"props":859,"children":861},{"className":860},[],[862],{"type":51,"value":863},"halted",{"type":51,"value":865}," — a guard fired (scope violation, unregistered new files, a dead or\nunavailable reviewer, or a finalize pass whose own edits failed the check that follows\nit). Relay the paths in ",{"type":46,"tag":60,"props":867,"children":869},{"className":868},[],[870],{"type":51,"value":871},"violations",{"type":51,"value":873},"\u002F",{"type":46,"tag":60,"props":875,"children":877},{"className":876},[],[878],{"type":51,"value":879},"new_untracked_files",{"type":51,"value":881},", the sites in\n",{"type":46,"tag":60,"props":883,"children":885},{"className":884},[],[886],{"type":51,"value":887},"finalize_regressions",{"type":51,"value":889},", and the notes.",{"type":46,"tag":100,"props":891,"children":892},{},[893,901],{"type":46,"tag":153,"props":894,"children":895},{},[896],{"type":46,"tag":60,"props":897,"children":899},{"className":898},[],[900],{"type":51,"value":489},{"type":51,"value":902}," always travel with the result — surface them; they include loud warnings\nsuch as \"a git repository was initialized\".",{"type":46,"tag":69,"props":904,"children":906},{"id":905},"continuing-after-an-escalation",[907],{"type":51,"value":908},"Continuing after an escalation",{"type":46,"tag":54,"props":910,"children":911},{},[912],{"type":51,"value":913},"The loop stops on escalation by design. When the user decides, start a fresh run with\nthe same args plus:",{"type":46,"tag":308,"props":915,"children":917},{"className":310,"code":916,"language":312,"meta":313,"style":313},"{ \"decision\": \"\u003Cthe user's ruling, verbatim>\" }\n",[918],{"type":46,"tag":60,"props":919,"children":920},{"__ignoreMap":313},[921],{"type":46,"tag":319,"props":922,"children":923},{"class":321,"line":322},[924,929,933,937,941,945,949,954,958],{"type":46,"tag":319,"props":925,"children":926},{"style":326},[927],{"type":51,"value":928},"{",{"type":46,"tag":319,"props":930,"children":931},{"style":326},[932],{"type":51,"value":358},{"type":46,"tag":319,"props":934,"children":935},{"style":341},[936],{"type":51,"value":699},{"type":46,"tag":319,"props":938,"children":939},{"style":326},[940],{"type":51,"value":349},{"type":46,"tag":319,"props":942,"children":943},{"style":326},[944],{"type":51,"value":306},{"type":46,"tag":319,"props":946,"children":947},{"style":326},[948],{"type":51,"value":358},{"type":46,"tag":319,"props":950,"children":951},{"style":361},[952],{"type":51,"value":953},"\u003Cthe user's ruling, verbatim>",{"type":46,"tag":319,"props":955,"children":956},{"style":326},[957],{"type":51,"value":349},{"type":46,"tag":319,"props":959,"children":960},{"style":326},[961],{"type":51,"value":962}," }\n",{"type":46,"tag":54,"props":964,"children":965},{},[966],{"type":51,"value":967},"The new run reloads the on-disk ledger, so every finding, rejection, and verdict carries\nover — rounds restart, re-derivation does not.",{"type":46,"tag":54,"props":969,"children":970},{},[971],{"type":51,"value":972},"To stop a running loop, stop the workflow task (TaskStop); the ledger on disk is current\nto the last round and a re-run resumes from it.",{"type":46,"tag":69,"props":974,"children":976},{"id":975},"when-not-to-use",[977],{"type":51,"value":978},"When NOT to use",{"type":46,"tag":639,"props":980,"children":981},{},[982,992,1010],{"type":46,"tag":100,"props":983,"children":984},{},[985,990],{"type":46,"tag":153,"props":986,"children":987},{},[988],{"type":51,"value":989},"One-time review",{"type":51,"value":991},": run the PR-review skill directly; the loop's value is iteration",{"type":46,"tag":100,"props":993,"children":994},{},[995,1000,1002,1008],{"type":46,"tag":153,"props":996,"children":997},{},[998],{"type":51,"value":999},"A skill",{"type":51,"value":1001},": use the ",{"type":46,"tag":60,"props":1003,"children":1005},{"className":1004},[],[1006],{"type":51,"value":1007},"skill-improver",{"type":51,"value":1009}," entry — it wires the right reviewer",{"type":46,"tag":100,"props":1011,"children":1012},{},[1013,1018],{"type":46,"tag":153,"props":1014,"children":1015},{},[1016],{"type":51,"value":1017},"Unpushed exploratory work",{"type":51,"value":1019},": review-and-fix loops harden a diff; while the shape is\nfluid, manual iteration gives more control",{"type":46,"tag":1021,"props":1022,"children":1023},"style",{},[1024],{"type":51,"value":1025},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1027,"total":1185},[1028,1047,1057,1077,1092,1104,1114,1127,1138,1150,1161,1172],{"slug":1029,"name":1029,"fn":1030,"description":1031,"org":1032,"tags":1033,"stars":26,"repoUrl":27,"updatedAt":1046},"address-sanitizer","detect memory errors during fuzzing","Builds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests. Covers -fsanitize=address builds, ASAN_OPTIONS, reading the crash report, LeakSanitizer, and the overhead and platform trade-offs. Use when fuzzing C\u002FC++ or Rust that has unsafe blocks or FFI, when debugging a memory corruption crash, or when reading an ASan stack trace.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1034,1037,1040,1043],{"name":1035,"slug":1036,"type":16},"C#","c",{"name":1038,"slug":1039,"type":16},"Debugging","debugging",{"name":1041,"slug":1042,"type":16},"Security","security",{"name":1044,"slug":1045,"type":16},"Testing","testing","2026-08-27T13:04:44.575925",{"slug":1048,"name":1048,"fn":1049,"description":1050,"org":1051,"tags":1052,"stars":26,"repoUrl":27,"updatedAt":1056},"aflpp","perform multi-core fuzzing of C\u002FC++ projects","Sets up and runs AFL++ for multi-core fuzzing of C\u002FC++ projects built with afl-clang-fast or afl-gcc-fast. Covers instrumentation modes, parallel main and secondary campaigns, persistent mode, corpus minimization, and crash triage. Use when scaling fuzzing across cores, fuzzing a mature C\u002FC++ codebase, reading the afl-fuzz status screen, or moving on after libFuzzer has plateaued.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1053,1054,1055],{"name":1035,"slug":1036,"type":16},{"name":1041,"slug":1042,"type":16},{"name":1044,"slug":1045,"type":16},"2026-08-27T13:05:05.242264",{"slug":1058,"name":1058,"fn":1059,"description":1060,"org":1061,"tags":1062,"stars":26,"repoUrl":27,"updatedAt":1076},"agentic-actions-auditor","audit GitHub Actions for security vulnerabilities","Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI\u002FCD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI\u002FCD pipeline security for prompt injection risks, or evaluating agentic action configurations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1063,1066,1069,1072,1075],{"name":1064,"slug":1065,"type":16},"Agents","agents",{"name":1067,"slug":1068,"type":16},"CI\u002FCD","ci-cd",{"name":1070,"slug":1071,"type":16},"Code Analysis","code-analysis",{"name":1073,"slug":1074,"type":16},"GitHub Actions","github-actions",{"name":1041,"slug":1042,"type":16},"2026-07-18T05:47:48.564744",{"slug":1078,"name":1078,"fn":1079,"description":1080,"org":1081,"tags":1082,"stars":26,"repoUrl":27,"updatedAt":1091},"algorand-vulnerability-scanner","scan Algorand smart contracts for vulnerabilities","Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use when auditing Algorand projects (TEAL\u002FPyTeal).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1083,1086,1087,1088],{"name":1084,"slug":1085,"type":16},"Audit","audit",{"name":1070,"slug":1071,"type":16},{"name":1041,"slug":1042,"type":16},{"name":1089,"slug":1090,"type":16},"Smart Contracts","smart-contracts","2026-08-21T03:32:34.227368",{"slug":1093,"name":1093,"fn":1094,"description":1095,"org":1096,"tags":1097,"stars":26,"repoUrl":27,"updatedAt":1103},"atheris","fuzz Python code with Atheris","Sets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer. Covers TestOneInput harnesses, FuzzedDataProvider, instrumenting both pure Python and native C extensions, and running under AddressSanitizer. Use when fuzzing a Python package, hunting memory corruption in a Python C extension, or choosing between Atheris and Hypothesis for a Python target.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1098,1101,1102],{"name":1099,"slug":1100,"type":16},"Python","python",{"name":1041,"slug":1042,"type":16},{"name":1044,"slug":1045,"type":16},"2026-08-27T13:04:51.552071",{"slug":1105,"name":1105,"fn":1106,"description":1107,"org":1108,"tags":1109,"stars":26,"repoUrl":27,"updatedAt":1113},"audit-augmentation","augment code graphs with audit findings","Augments Trailmark code graphs with external audit findings from SARIF static analysis results, weAudit annotation files, and version-gated Trailmark 0.4.x binary-analysis graph exports. Maps findings to graph nodes by file and line overlap, creates severity-based subgraphs, and enables cross-referencing findings with pre-analysis data (blast radius, taint, etc.). Use when projecting SARIF results onto a code graph, overlaying weAudit annotations, importing binary graph findings, cross-referencing Semgrep, CodeQL, or binary-analysis findings with call graph data, or visualizing audit findings in the context of code structure.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1110,1111,1112],{"name":1084,"slug":1085,"type":16},{"name":1070,"slug":1071,"type":16},{"name":1041,"slug":1042,"type":16},"2026-08-21T03:32:38.432332",{"slug":1115,"name":1115,"fn":1116,"description":1117,"org":1118,"tags":1119,"stars":26,"repoUrl":27,"updatedAt":1126},"audit-context-building","build architectural context for code analysis","Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1120,1123,1124,1125],{"name":1121,"slug":1122,"type":16},"Architecture","architecture",{"name":1084,"slug":1085,"type":16},{"name":1070,"slug":1071,"type":16},{"name":21,"slug":22,"type":16},"2026-08-08T03:55:04.309014",{"slug":1128,"name":1128,"fn":1129,"description":1130,"org":1131,"tags":1132,"stars":26,"repoUrl":27,"updatedAt":1137},"audit-prep-assistant","prepare codebases for security audits","Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation (flowcharts, user stories, inline comments). Use when preparing your own codebase to be audited by someone else, getting a repository review-ready before an external security review, deciding what to fix before auditors start, or asking what assessors need from a project. For understanding unfamiliar code you are about to audit, use audit-context-building instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1133,1134,1135,1136],{"name":1084,"slug":1085,"type":16},{"name":1070,"slug":1071,"type":16},{"name":21,"slug":22,"type":16},{"name":1041,"slug":1042,"type":16},"2026-08-27T13:05:06.207058",{"slug":1139,"name":1139,"fn":1140,"description":1141,"org":1142,"tags":1143,"stars":26,"repoUrl":27,"updatedAt":1149},"burpsuite-project-parser","parse Burp Suite project files","Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting security audit findings, dumping proxy history or site map data, or analyzing HTTP traffic captured in a Burp project.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1144,1145,1148],{"name":1084,"slug":1085,"type":16},{"name":1146,"slug":1147,"type":16},"CLI","cli",{"name":1041,"slug":1042,"type":16},"2026-07-17T06:05:33.198077",{"slug":1151,"name":1151,"fn":1152,"description":1153,"org":1154,"tags":1155,"stars":26,"repoUrl":27,"updatedAt":1160},"c-review","audit C and C++ code","Performs comprehensive C\u002FC++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities. Use when auditing native C\u002FC++ applications, reviewing daemons or services for memory safety, or hunting integer overflow \u002F use-after-free \u002F race conditions in userspace code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1156,1157,1158,1159],{"name":1084,"slug":1085,"type":16},{"name":1035,"slug":1036,"type":16},{"name":1070,"slug":1071,"type":16},{"name":1041,"slug":1042,"type":16},"2026-08-27T13:04:50.663101",{"slug":1162,"name":1162,"fn":1163,"description":1164,"org":1165,"tags":1166,"stars":26,"repoUrl":27,"updatedAt":1171},"cairo-vulnerability-scanner","scan Cairo and StarkNet contracts for vulnerabilities","Scans Cairo\u002FStarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging issues, address conversion problems, and signature replay. Use when auditing StarkNet projects.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1167,1168,1169,1170],{"name":1084,"slug":1085,"type":16},{"name":1070,"slug":1071,"type":16},{"name":1041,"slug":1042,"type":16},{"name":1089,"slug":1090,"type":16},"2026-08-21T03:32:39.232318",{"slug":1173,"name":1173,"fn":1174,"description":1175,"org":1176,"tags":1177,"stars":26,"repoUrl":27,"updatedAt":1184},"cargo-fuzz","fuzz Rust projects with cargo-fuzz","Sets up and runs cargo-fuzz, the standard fuzzing tool for Cargo-based Rust projects. Covers cargo fuzz init, the nightly toolchain requirement, fuzz_target! harnesses, Arbitrary-derived structured inputs, sanitizer options, cargo fuzz coverage, and reproducing a crash artifact. Use when fuzzing a Rust crate, writing a fuzz_target!, exercising unsafe blocks or FFI in Rust, or triaging a cargo fuzz crash.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1178,1179,1182,1183],{"name":21,"slug":22,"type":16},{"name":1180,"slug":1181,"type":16},"Rust","rust",{"name":1041,"slug":1042,"type":16},{"name":1044,"slug":1045,"type":16},"2026-08-27T13:04:42.229129",112,{"items":1187,"total":1235},[1188,1195,1201,1209,1216,1222,1228],{"slug":1029,"name":1029,"fn":1030,"description":1031,"org":1189,"tags":1190,"stars":26,"repoUrl":27,"updatedAt":1046},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1191,1192,1193,1194],{"name":1035,"slug":1036,"type":16},{"name":1038,"slug":1039,"type":16},{"name":1041,"slug":1042,"type":16},{"name":1044,"slug":1045,"type":16},{"slug":1048,"name":1048,"fn":1049,"description":1050,"org":1196,"tags":1197,"stars":26,"repoUrl":27,"updatedAt":1056},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1198,1199,1200],{"name":1035,"slug":1036,"type":16},{"name":1041,"slug":1042,"type":16},{"name":1044,"slug":1045,"type":16},{"slug":1058,"name":1058,"fn":1059,"description":1060,"org":1202,"tags":1203,"stars":26,"repoUrl":27,"updatedAt":1076},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1204,1205,1206,1207,1208],{"name":1064,"slug":1065,"type":16},{"name":1067,"slug":1068,"type":16},{"name":1070,"slug":1071,"type":16},{"name":1073,"slug":1074,"type":16},{"name":1041,"slug":1042,"type":16},{"slug":1078,"name":1078,"fn":1079,"description":1080,"org":1210,"tags":1211,"stars":26,"repoUrl":27,"updatedAt":1091},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1212,1213,1214,1215],{"name":1084,"slug":1085,"type":16},{"name":1070,"slug":1071,"type":16},{"name":1041,"slug":1042,"type":16},{"name":1089,"slug":1090,"type":16},{"slug":1093,"name":1093,"fn":1094,"description":1095,"org":1217,"tags":1218,"stars":26,"repoUrl":27,"updatedAt":1103},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1219,1220,1221],{"name":1099,"slug":1100,"type":16},{"name":1041,"slug":1042,"type":16},{"name":1044,"slug":1045,"type":16},{"slug":1105,"name":1105,"fn":1106,"description":1107,"org":1223,"tags":1224,"stars":26,"repoUrl":27,"updatedAt":1113},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1225,1226,1227],{"name":1084,"slug":1085,"type":16},{"name":1070,"slug":1071,"type":16},{"name":1041,"slug":1042,"type":16},{"slug":1115,"name":1115,"fn":1116,"description":1117,"org":1229,"tags":1230,"stars":26,"repoUrl":27,"updatedAt":1126},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1231,1232,1233,1234],{"name":1121,"slug":1122,"type":16},{"name":1084,"slug":1085,"type":16},{"name":1070,"slug":1071,"type":16},{"name":21,"slug":22,"type":16},78]