[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-trail-of-bits-code-improver":3,"mdc--grxfao-key":38,"related-org-trail-of-bits-code-improver":1023,"related-repo-trail-of-bits-code-improver":1181},{"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},"code-improver","run autonomous code improvement loops","Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names: any installed skill or agent. Keeps a cross-round findings ledger, escalates when fixes stop converging, and guards scope mechanically. Use when asked to 'improve this code until review passes', 'run an improvement loop with \u003Creviewer>', or to iterate review-and-fix with a specific reviewer. For skills prefer the skill-improver entry; for a branch prefer pr-improver.",{"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},"Code Generation","code-generation","tag",{"name":18,"slug":19,"type":16},"Automation","automation",{"name":21,"slug":22,"type":16},"Engineering","engineering",{"name":24,"slug":25,"type":16},"Code Analysis","code-analysis",6139,"https:\u002F\u002Fgithub.com\u002Ftrailofbits\u002Fskills","2026-08-27T13:31:52.88145",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\u002Fcode-improver","---\nname: code-improver\ndescription: \"Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names: any installed skill or agent. Keeps a cross-round findings ledger, escalates when fixes stop converging, and guards scope mechanically. Use when asked to 'improve this code until review passes', 'run an improvement loop with \u003Creviewer>', or to iterate review-and-fix with a specific reviewer. For skills prefer the skill-improver entry; for a branch prefer pr-improver.\"\nargument-hint: \"\u003CTARGET_PATH> --reviewer \u003Cagent-or-skill-name> --scope \u003Cglobs> [--max-rounds N]\"\nallowed-tools: Bash Glob Read TaskOutput TaskStop Workflow\n---\n\n# Code Improver\n\nImprove any code target by running `\u002Fcode-improver:improve` — a dynamic workflow that\nloops the named reviewer and a fixer subagent until a review reports zero critical\u002Fmajor\nfindings, then strips its own residue. The loop, its ledger, and its guards live in the\nworkflow; this skill collects the three inputs the generic entry requires and relays the\noutcome.\n\n## Starting the loop\n\nThe user provided: `$ARGUMENTS` (if empty, take the details from the conversation).\n\n### 1. Collect the three required inputs — no guessing\n\n1. **Target**: the absolute path to the directory under improvement. Resolve relative\n   paths against the working directory; verify the directory exists.\n2. **Reviewer**: the installed skill or agent that performs every review. The user must\n   name it — there is no default and no bundled reviewer. Determine the kind:\n   - a namespaced agent (e.g. `plugin-dev:skill-reviewer`) → `\"kind\": \"agent\"`\n   - an installed skill (e.g. `pr-review-toolkit:review-pr`) → `\"kind\": \"skill\"`\n   If the name could be either, check the session's skill listing; if still ambiguous,\n   ask the user. If no reviewer was named, ask — do not pick one.\n3. **Scope**: repo-relative globs the loop may touch. The generic entry requires it\n   explicitly; if the user did not give one, propose the target directory\n   (`\u003Crepo-relative-target>\u002F**`) and confirm before launching.\n\n### 2. Resolve the loop script\n\nThe loop is the dynamic workflow `workflows\u002Fimprove.js` in this plugin. Launch it by\npath: `scriptPath` takes a resolved absolute path, and the Workflow tool's `name` resolves\nbuilt-in and project workflows, so a marketplace-installed one may not answer to\n`code-improver:improve`. Try in order, first hit wins — the home directories come before\n`.` so an installed copy beats a checkout of this marketplace:\n\n1. `Bash: ls -d -- \"${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\": \"\u003Cabsolute target path>\",\n  \"reviewer\": { \"kind\": \"agent|skill\", \"name\": \"\u003Cnamespaced-name>\", \"notes\": \"\u003Cwhat the reviewer should know about the target>\" },\n  \"scope\": [\"\u003Crepo-relative-glob>\u002F**\"],\n  \"pluginRoot\": \"\u003Cthe plugin directory from step 2>\",\n  \"maxRounds\": 5\n}\n```\n\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` (`{\"version_bump\": bool, \"narration_strip\": bool, \"docs_pass\": bool}`) only\n  to override the defaults: version bump when the target sits inside a plugin, narration\n  strip and docs pass always.\n- `decision` only on continuation (below).\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 named\nreviewer is not installed in this session; tell the user which plugin provides it and\nre-run after installing. Do not review the target yourself.\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 `target` and `reviewer` 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- **A Claude Code skill**: use the `skill-improver` entry — it wires the right reviewer\n- **A branch \u002F pull request**: use the `pr-improver` entry — it derives scope from the diff\n- **One-time review**: dispatch the reviewer directly; the loop's value is iteration\n- **Quick single fixes**: edit the file directly\n",{"data":39,"body":42},{"name":4,"description":6,"argument-hint":40,"allowed-tools":41},"\u003CTARGET_PATH> --reviewer \u003Cagent-or-skill-name> --scope \u003Cglobs> [--max-rounds N]","Bash Glob Read TaskOutput TaskStop Workflow",{"type":43,"children":44},"root",[45,53,68,75,88,95,182,188,233,265,294,300,313,627,680,685,695,713,723,729,734,869,875,894,943,948,953,959,1017],{"type":46,"tag":47,"props":48,"children":49},"element","h1",{"id":4},[50],{"type":51,"value":52},"text","Code Improver",{"type":46,"tag":54,"props":55,"children":56},"p",{},[57,59,66],{"type":51,"value":58},"Improve any code target 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 the named reviewer and a fixer subagent until a review reports zero critical\u002Fmajor\nfindings, then strips its own residue. The loop, its ledger, and its guards live in the\nworkflow; this skill collects the three inputs the generic entry requires and relays the\noutcome.",{"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 the details from the conversation).",{"type":46,"tag":89,"props":90,"children":92},"h3",{"id":91},"_1-collect-the-three-required-inputs-no-guessing",[93],{"type":51,"value":94},"1. Collect the three required inputs — no guessing",{"type":46,"tag":96,"props":97,"children":98},"ol",{},[99,111,164],{"type":46,"tag":100,"props":101,"children":102},"li",{},[103,109],{"type":46,"tag":104,"props":105,"children":106},"strong",{},[107],{"type":51,"value":108},"Target",{"type":51,"value":110},": the absolute path to the directory under improvement. Resolve relative\npaths against the working directory; verify the directory exists.",{"type":46,"tag":100,"props":112,"children":113},{},[114,119,121],{"type":46,"tag":104,"props":115,"children":116},{},[117],{"type":51,"value":118},"Reviewer",{"type":51,"value":120},": the installed skill or agent that performs every review. The user must\nname it — there is no default and no bundled reviewer. Determine the kind:\n",{"type":46,"tag":122,"props":123,"children":124},"ul",{},[125,144],{"type":46,"tag":100,"props":126,"children":127},{},[128,130,136,138],{"type":51,"value":129},"a namespaced agent (e.g. ",{"type":46,"tag":60,"props":131,"children":133},{"className":132},[],[134],{"type":51,"value":135},"plugin-dev:skill-reviewer",{"type":51,"value":137},") → ",{"type":46,"tag":60,"props":139,"children":141},{"className":140},[],[142],{"type":51,"value":143},"\"kind\": \"agent\"",{"type":46,"tag":100,"props":145,"children":146},{},[147,149,155,156,162],{"type":51,"value":148},"an installed skill (e.g. ",{"type":46,"tag":60,"props":150,"children":152},{"className":151},[],[153],{"type":51,"value":154},"pr-review-toolkit:review-pr",{"type":51,"value":137},{"type":46,"tag":60,"props":157,"children":159},{"className":158},[],[160],{"type":51,"value":161},"\"kind\": \"skill\"",{"type":51,"value":163},"\nIf the name could be either, check the session's skill listing; if still ambiguous,\nask the user. If no reviewer was named, ask — do not pick one.",{"type":46,"tag":100,"props":165,"children":166},{},[167,172,174,180],{"type":46,"tag":104,"props":168,"children":169},{},[170],{"type":51,"value":171},"Scope",{"type":51,"value":173},": repo-relative globs the loop may touch. The generic entry requires it\nexplicitly; if the user did not give one, propose the target directory\n(",{"type":46,"tag":60,"props":175,"children":177},{"className":176},[],[178],{"type":51,"value":179},"\u003Crepo-relative-target>\u002F**",{"type":51,"value":181},") and confirm before launching.",{"type":46,"tag":89,"props":183,"children":185},{"id":184},"_2-resolve-the-loop-script",[186],{"type":51,"value":187},"2. Resolve the loop script",{"type":46,"tag":54,"props":189,"children":190},{},[191,193,199,201,207,209,215,217,223,225,231],{"type":51,"value":192},"The loop is the dynamic workflow ",{"type":46,"tag":60,"props":194,"children":196},{"className":195},[],[197],{"type":51,"value":198},"workflows\u002Fimprove.js",{"type":51,"value":200}," in this plugin. Launch it by\npath: ",{"type":46,"tag":60,"props":202,"children":204},{"className":203},[],[205],{"type":51,"value":206},"scriptPath",{"type":51,"value":208}," takes a resolved absolute path, and the Workflow tool's ",{"type":46,"tag":60,"props":210,"children":212},{"className":211},[],[213],{"type":51,"value":214},"name",{"type":51,"value":216}," resolves\nbuilt-in and project workflows, so a marketplace-installed one may not answer to\n",{"type":46,"tag":60,"props":218,"children":220},{"className":219},[],[221],{"type":51,"value":222},"code-improver:improve",{"type":51,"value":224},". Try in order, first hit wins — the home directories come before\n",{"type":46,"tag":60,"props":226,"children":228},{"className":227},[],[229],{"type":51,"value":230},".",{"type":51,"value":232}," so an installed copy beats a checkout of this marketplace:",{"type":46,"tag":96,"props":234,"children":235},{},[236,245,256],{"type":46,"tag":100,"props":237,"children":238},{},[239],{"type":46,"tag":60,"props":240,"children":242},{"className":241},[],[243],{"type":51,"value":244},"Bash: ls -d -- \"${CLAUDE_PLUGIN_ROOT}\u002Fworkflows\u002Fimprove.js\"",{"type":46,"tag":100,"props":246,"children":247},{},[248,254],{"type":46,"tag":60,"props":249,"children":251},{"className":250},[],[252],{"type":51,"value":253},"Bash: ls -d -- \"${CODEX_PLUGIN_ROOT}\u002Fworkflows\u002Fimprove.js\"",{"type":51,"value":255}," (if that variable is set instead)",{"type":46,"tag":100,"props":257,"children":258},{},[259],{"type":46,"tag":60,"props":260,"children":262},{"className":261},[],[263],{"type":51,"value":264},"Bash: find ~\u002F.claude ~\u002F.codex . -maxdepth 7 -path '*\u002Fcode-improver\u002Fworkflows\u002Fimprove.js' -print -quit 2>\u002Fdev\u002Fnull",{"type":46,"tag":54,"props":266,"children":267},{},[268,270,276,278,284,286,292],{"type":51,"value":269},"Use the path exactly as printed. Its plugin directory — the path with\n",{"type":46,"tag":60,"props":271,"children":273},{"className":272},[],[274],{"type":51,"value":275},"\u002Fworkflows\u002Fimprove.js",{"type":51,"value":277}," removed — is ",{"type":46,"tag":60,"props":279,"children":281},{"className":280},[],[282],{"type":51,"value":283},"pluginRoot",{"type":51,"value":285},". If all three come back empty, try\n",{"type":46,"tag":60,"props":287,"children":289},{"className":288},[],[290],{"type":51,"value":291},"{name: \"code-improver:improve\"}",{"type":51,"value":293}," 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":295,"children":297},{"id":296},"_3-invoke-the-workflow",[298],{"type":51,"value":299},"3. Invoke the workflow",{"type":46,"tag":54,"props":301,"children":302},{},[303,305,311],{"type":51,"value":304},"Run it with the Workflow tool, ",{"type":46,"tag":60,"props":306,"children":308},{"className":307},[],[309],{"type":51,"value":310},"{scriptPath: \"\u003Cthe path from step 2>\", args: {...}}",{"type":51,"value":312},":",{"type":46,"tag":314,"props":315,"children":320},"pre",{"className":316,"code":317,"language":318,"meta":319,"style":319},"language-json shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","{\n  \"target\": \"\u003Cabsolute target path>\",\n  \"reviewer\": { \"kind\": \"agent|skill\", \"name\": \"\u003Cnamespaced-name>\", \"notes\": \"\u003Cwhat the reviewer should know about the target>\" },\n  \"scope\": [\"\u003Crepo-relative-glob>\u002F**\"],\n  \"pluginRoot\": \"\u003Cthe plugin directory from step 2>\",\n  \"maxRounds\": 5\n}\n","json","",[321],{"type":46,"tag":60,"props":322,"children":323},{"__ignoreMap":319},[324,336,380,510,554,591,618],{"type":46,"tag":325,"props":326,"children":329},"span",{"class":327,"line":328},"line",1,[330],{"type":46,"tag":325,"props":331,"children":333},{"style":332},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[334],{"type":51,"value":335},"{\n",{"type":46,"tag":325,"props":337,"children":339},{"class":327,"line":338},2,[340,345,351,356,360,365,371,375],{"type":46,"tag":325,"props":341,"children":342},{"style":332},[343],{"type":51,"value":344},"  \"",{"type":46,"tag":325,"props":346,"children":348},{"style":347},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[349],{"type":51,"value":350},"target",{"type":46,"tag":325,"props":352,"children":353},{"style":332},[354],{"type":51,"value":355},"\"",{"type":46,"tag":325,"props":357,"children":358},{"style":332},[359],{"type":51,"value":312},{"type":46,"tag":325,"props":361,"children":362},{"style":332},[363],{"type":51,"value":364}," \"",{"type":46,"tag":325,"props":366,"children":368},{"style":367},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[369],{"type":51,"value":370},"\u003Cabsolute target path>",{"type":46,"tag":325,"props":372,"children":373},{"style":332},[374],{"type":51,"value":355},{"type":46,"tag":325,"props":376,"children":377},{"style":332},[378],{"type":51,"value":379},",\n",{"type":46,"tag":325,"props":381,"children":383},{"class":327,"line":382},3,[384,388,393,397,401,406,410,416,420,424,428,433,437,442,446,450,454,458,462,467,471,475,479,484,488,492,496,501,505],{"type":46,"tag":325,"props":385,"children":386},{"style":332},[387],{"type":51,"value":344},{"type":46,"tag":325,"props":389,"children":390},{"style":347},[391],{"type":51,"value":392},"reviewer",{"type":46,"tag":325,"props":394,"children":395},{"style":332},[396],{"type":51,"value":355},{"type":46,"tag":325,"props":398,"children":399},{"style":332},[400],{"type":51,"value":312},{"type":46,"tag":325,"props":402,"children":403},{"style":332},[404],{"type":51,"value":405}," {",{"type":46,"tag":325,"props":407,"children":408},{"style":332},[409],{"type":51,"value":364},{"type":46,"tag":325,"props":411,"children":413},{"style":412},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[414],{"type":51,"value":415},"kind",{"type":46,"tag":325,"props":417,"children":418},{"style":332},[419],{"type":51,"value":355},{"type":46,"tag":325,"props":421,"children":422},{"style":332},[423],{"type":51,"value":312},{"type":46,"tag":325,"props":425,"children":426},{"style":332},[427],{"type":51,"value":364},{"type":46,"tag":325,"props":429,"children":430},{"style":367},[431],{"type":51,"value":432},"agent|skill",{"type":46,"tag":325,"props":434,"children":435},{"style":332},[436],{"type":51,"value":355},{"type":46,"tag":325,"props":438,"children":439},{"style":332},[440],{"type":51,"value":441},",",{"type":46,"tag":325,"props":443,"children":444},{"style":332},[445],{"type":51,"value":364},{"type":46,"tag":325,"props":447,"children":448},{"style":412},[449],{"type":51,"value":214},{"type":46,"tag":325,"props":451,"children":452},{"style":332},[453],{"type":51,"value":355},{"type":46,"tag":325,"props":455,"children":456},{"style":332},[457],{"type":51,"value":312},{"type":46,"tag":325,"props":459,"children":460},{"style":332},[461],{"type":51,"value":364},{"type":46,"tag":325,"props":463,"children":464},{"style":367},[465],{"type":51,"value":466},"\u003Cnamespaced-name>",{"type":46,"tag":325,"props":468,"children":469},{"style":332},[470],{"type":51,"value":355},{"type":46,"tag":325,"props":472,"children":473},{"style":332},[474],{"type":51,"value":441},{"type":46,"tag":325,"props":476,"children":477},{"style":332},[478],{"type":51,"value":364},{"type":46,"tag":325,"props":480,"children":481},{"style":412},[482],{"type":51,"value":483},"notes",{"type":46,"tag":325,"props":485,"children":486},{"style":332},[487],{"type":51,"value":355},{"type":46,"tag":325,"props":489,"children":490},{"style":332},[491],{"type":51,"value":312},{"type":46,"tag":325,"props":493,"children":494},{"style":332},[495],{"type":51,"value":364},{"type":46,"tag":325,"props":497,"children":498},{"style":367},[499],{"type":51,"value":500},"\u003Cwhat the reviewer should know about the target>",{"type":46,"tag":325,"props":502,"children":503},{"style":332},[504],{"type":51,"value":355},{"type":46,"tag":325,"props":506,"children":507},{"style":332},[508],{"type":51,"value":509}," },\n",{"type":46,"tag":325,"props":511,"children":513},{"class":327,"line":512},4,[514,518,523,527,531,536,540,545,549],{"type":46,"tag":325,"props":515,"children":516},{"style":332},[517],{"type":51,"value":344},{"type":46,"tag":325,"props":519,"children":520},{"style":347},[521],{"type":51,"value":522},"scope",{"type":46,"tag":325,"props":524,"children":525},{"style":332},[526],{"type":51,"value":355},{"type":46,"tag":325,"props":528,"children":529},{"style":332},[530],{"type":51,"value":312},{"type":46,"tag":325,"props":532,"children":533},{"style":332},[534],{"type":51,"value":535}," [",{"type":46,"tag":325,"props":537,"children":538},{"style":332},[539],{"type":51,"value":355},{"type":46,"tag":325,"props":541,"children":542},{"style":367},[543],{"type":51,"value":544},"\u003Crepo-relative-glob>\u002F**",{"type":46,"tag":325,"props":546,"children":547},{"style":332},[548],{"type":51,"value":355},{"type":46,"tag":325,"props":550,"children":551},{"style":332},[552],{"type":51,"value":553},"],\n",{"type":46,"tag":325,"props":555,"children":557},{"class":327,"line":556},5,[558,562,566,570,574,578,583,587],{"type":46,"tag":325,"props":559,"children":560},{"style":332},[561],{"type":51,"value":344},{"type":46,"tag":325,"props":563,"children":564},{"style":347},[565],{"type":51,"value":283},{"type":46,"tag":325,"props":567,"children":568},{"style":332},[569],{"type":51,"value":355},{"type":46,"tag":325,"props":571,"children":572},{"style":332},[573],{"type":51,"value":312},{"type":46,"tag":325,"props":575,"children":576},{"style":332},[577],{"type":51,"value":364},{"type":46,"tag":325,"props":579,"children":580},{"style":367},[581],{"type":51,"value":582},"\u003Cthe plugin directory from step 2>",{"type":46,"tag":325,"props":584,"children":585},{"style":332},[586],{"type":51,"value":355},{"type":46,"tag":325,"props":588,"children":589},{"style":332},[590],{"type":51,"value":379},{"type":46,"tag":325,"props":592,"children":594},{"class":327,"line":593},6,[595,599,604,608,612],{"type":46,"tag":325,"props":596,"children":597},{"style":332},[598],{"type":51,"value":344},{"type":46,"tag":325,"props":600,"children":601},{"style":347},[602],{"type":51,"value":603},"maxRounds",{"type":46,"tag":325,"props":605,"children":606},{"style":332},[607],{"type":51,"value":355},{"type":46,"tag":325,"props":609,"children":610},{"style":332},[611],{"type":51,"value":312},{"type":46,"tag":325,"props":613,"children":615},{"style":614},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[616],{"type":51,"value":617}," 5\n",{"type":46,"tag":325,"props":619,"children":621},{"class":327,"line":620},7,[622],{"type":46,"tag":325,"props":623,"children":624},{"style":332},[625],{"type":51,"value":626},"}\n",{"type":46,"tag":122,"props":628,"children":629},{},[630,640,650,669],{"type":46,"tag":100,"props":631,"children":632},{},[633,638],{"type":46,"tag":60,"props":634,"children":636},{"className":635},[],[637],{"type":51,"value":603},{"type":51,"value":639}," only if the user asked for a different cap.",{"type":46,"tag":100,"props":641,"children":642},{},[643,648],{"type":46,"tag":60,"props":644,"children":646},{"className":645},[],[647],{"type":51,"value":283},{"type":51,"value":649}," 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":651,"children":652},{},[653,659,661,667],{"type":46,"tag":60,"props":654,"children":656},{"className":655},[],[657],{"type":51,"value":658},"finalize",{"type":51,"value":660}," (",{"type":46,"tag":60,"props":662,"children":664},{"className":663},[],[665],{"type":51,"value":666},"{\"version_bump\": bool, \"narration_strip\": bool, \"docs_pass\": bool}",{"type":51,"value":668},") only\nto override the defaults: version bump when the target sits inside a plugin, narration\nstrip and docs pass always.",{"type":46,"tag":100,"props":670,"children":671},{},[672,678],{"type":46,"tag":60,"props":673,"children":675},{"className":674},[],[676],{"type":51,"value":677},"decision",{"type":51,"value":679}," only on continuation (below).",{"type":46,"tag":54,"props":681,"children":682},{},[683],{"type":51,"value":684},"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":686,"children":687},{},[688,693],{"type":46,"tag":104,"props":689,"children":690},{},[691],{"type":51,"value":692},"If the Workflow tool is unavailable or denied, stop and say so.",{"type":51,"value":694}," 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":696,"children":697},{},[698,711],{"type":46,"tag":104,"props":699,"children":700},{},[701,703,709],{"type":51,"value":702},"If the result is ",{"type":46,"tag":60,"props":704,"children":706},{"className":705},[],[707],{"type":51,"value":708},"halted: \"reviewer-unavailable\"",{"type":51,"value":710},", relay it and stop.",{"type":51,"value":712}," The named\nreviewer is not installed in this session; tell the user which plugin provides it and\nre-run after installing. Do not review the target yourself.",{"type":46,"tag":54,"props":714,"children":715},{},[716,721],{"type":46,"tag":104,"props":717,"children":718},{},[719],{"type":51,"value":720},"Do not end your turn while the loop is running.",{"type":51,"value":722}," 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":724,"children":726},{"id":725},"relaying-the-result",[727],{"type":51,"value":728},"Relaying the result",{"type":46,"tag":54,"props":730,"children":731},{},[732],{"type":51,"value":733},"The workflow returns a structured result. Report it honestly — the distinctions matter:",{"type":46,"tag":122,"props":735,"children":736},{},[737,775,804,818,856],{"type":46,"tag":100,"props":738,"children":739},{},[740,749,751,757,759,765,767,773],{"type":46,"tag":104,"props":741,"children":742},{},[743],{"type":46,"tag":60,"props":744,"children":746},{"className":745},[],[747],{"type":51,"value":748},"converged: true",{"type":51,"value":750}," — the last action was a review with zero critical\u002Fmajor findings.\nReport rounds used, remaining minor findings (",{"type":46,"tag":60,"props":752,"children":754},{"className":753},[],[755],{"type":51,"value":756},"open_minor_count",{"type":51,"value":758},"), and the artifact\npaths (",{"type":46,"tag":60,"props":760,"children":762},{"className":761},[],[763],{"type":51,"value":764},"ledger_path",{"type":51,"value":766},", ",{"type":46,"tag":60,"props":768,"children":770},{"className":769},[],[771],{"type":51,"value":772},"metrics",{"type":51,"value":774},").",{"type":46,"tag":100,"props":776,"children":777},{},[778,787,789,794,796,802],{"type":46,"tag":104,"props":779,"children":780},{},[781],{"type":46,"tag":60,"props":782,"children":784},{"className":783},[],[785],{"type":51,"value":786},"capped: true",{"type":51,"value":788}," — the fix budget ran out and the FINAL review still found blocking\nissues. Say plainly: ",{"type":46,"tag":104,"props":790,"children":791},{},[792],{"type":51,"value":793},"capped, NOT converged",{"type":51,"value":795},", and list ",{"type":46,"tag":60,"props":797,"children":799},{"className":798},[],[800],{"type":51,"value":801},"open_blocking",{"type":51,"value":803},". Do not\npresent this as success.",{"type":46,"tag":100,"props":805,"children":806},{},[807,816],{"type":46,"tag":104,"props":808,"children":809},{},[810],{"type":46,"tag":60,"props":811,"children":813},{"className":812},[],[814],{"type":51,"value":815},"escalation",{"type":51,"value":817}," — 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":819,"children":820},{},[821,830,832,838,840,846,848,854],{"type":46,"tag":104,"props":822,"children":823},{},[824],{"type":46,"tag":60,"props":825,"children":827},{"className":826},[],[828],{"type":51,"value":829},"halted",{"type":51,"value":831}," — 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":833,"children":835},{"className":834},[],[836],{"type":51,"value":837},"violations",{"type":51,"value":839},"\u002F",{"type":46,"tag":60,"props":841,"children":843},{"className":842},[],[844],{"type":51,"value":845},"new_untracked_files",{"type":51,"value":847},", the sites in\n",{"type":46,"tag":60,"props":849,"children":851},{"className":850},[],[852],{"type":51,"value":853},"finalize_regressions",{"type":51,"value":855},", and the notes.",{"type":46,"tag":100,"props":857,"children":858},{},[859,867],{"type":46,"tag":104,"props":860,"children":861},{},[862],{"type":46,"tag":60,"props":863,"children":865},{"className":864},[],[866],{"type":51,"value":483},{"type":51,"value":868}," always travel with the result — surface them; they include loud warnings\nsuch as \"a git repository was initialized\".",{"type":46,"tag":69,"props":870,"children":872},{"id":871},"continuing-after-an-escalation",[873],{"type":51,"value":874},"Continuing after an escalation",{"type":46,"tag":54,"props":876,"children":877},{},[878,880,885,887,892],{"type":51,"value":879},"The loop stops on escalation by design. When the user decides, start a fresh run with\nthe same ",{"type":46,"tag":60,"props":881,"children":883},{"className":882},[],[884],{"type":51,"value":350},{"type":51,"value":886}," and ",{"type":46,"tag":60,"props":888,"children":890},{"className":889},[],[891],{"type":51,"value":392},{"type":51,"value":893}," plus:",{"type":46,"tag":314,"props":895,"children":897},{"className":316,"code":896,"language":318,"meta":319,"style":319},"{ \"decision\": \"\u003Cthe user's ruling, verbatim>\" }\n",[898],{"type":46,"tag":60,"props":899,"children":900},{"__ignoreMap":319},[901],{"type":46,"tag":325,"props":902,"children":903},{"class":327,"line":328},[904,909,913,917,921,925,929,934,938],{"type":46,"tag":325,"props":905,"children":906},{"style":332},[907],{"type":51,"value":908},"{",{"type":46,"tag":325,"props":910,"children":911},{"style":332},[912],{"type":51,"value":364},{"type":46,"tag":325,"props":914,"children":915},{"style":347},[916],{"type":51,"value":677},{"type":46,"tag":325,"props":918,"children":919},{"style":332},[920],{"type":51,"value":355},{"type":46,"tag":325,"props":922,"children":923},{"style":332},[924],{"type":51,"value":312},{"type":46,"tag":325,"props":926,"children":927},{"style":332},[928],{"type":51,"value":364},{"type":46,"tag":325,"props":930,"children":931},{"style":367},[932],{"type":51,"value":933},"\u003Cthe user's ruling, verbatim>",{"type":46,"tag":325,"props":935,"children":936},{"style":332},[937],{"type":51,"value":355},{"type":46,"tag":325,"props":939,"children":940},{"style":332},[941],{"type":51,"value":942}," }\n",{"type":46,"tag":54,"props":944,"children":945},{},[946],{"type":51,"value":947},"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":949,"children":950},{},[951],{"type":51,"value":952},"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":954,"children":956},{"id":955},"when-not-to-use",[957],{"type":51,"value":958},"When NOT to use",{"type":46,"tag":122,"props":960,"children":961},{},[962,980,997,1007],{"type":46,"tag":100,"props":963,"children":964},{},[965,970,972,978],{"type":46,"tag":104,"props":966,"children":967},{},[968],{"type":51,"value":969},"A Claude Code skill",{"type":51,"value":971},": use the ",{"type":46,"tag":60,"props":973,"children":975},{"className":974},[],[976],{"type":51,"value":977},"skill-improver",{"type":51,"value":979}," entry — it wires the right reviewer",{"type":46,"tag":100,"props":981,"children":982},{},[983,988,989,995],{"type":46,"tag":104,"props":984,"children":985},{},[986],{"type":51,"value":987},"A branch \u002F pull request",{"type":51,"value":971},{"type":46,"tag":60,"props":990,"children":992},{"className":991},[],[993],{"type":51,"value":994},"pr-improver",{"type":51,"value":996}," entry — it derives scope from the diff",{"type":46,"tag":100,"props":998,"children":999},{},[1000,1005],{"type":46,"tag":104,"props":1001,"children":1002},{},[1003],{"type":51,"value":1004},"One-time review",{"type":51,"value":1006},": dispatch the reviewer directly; the loop's value is iteration",{"type":46,"tag":100,"props":1008,"children":1009},{},[1010,1015],{"type":46,"tag":104,"props":1011,"children":1012},{},[1013],{"type":51,"value":1014},"Quick single fixes",{"type":51,"value":1016},": edit the file directly",{"type":46,"tag":1018,"props":1019,"children":1020},"style",{},[1021],{"type":51,"value":1022},"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":1024,"total":1180},[1025,1044,1054,1072,1087,1099,1109,1122,1133,1145,1156,1167],{"slug":1026,"name":1026,"fn":1027,"description":1028,"org":1029,"tags":1030,"stars":26,"repoUrl":27,"updatedAt":1043},"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},[1031,1034,1037,1040],{"name":1032,"slug":1033,"type":16},"C#","c",{"name":1035,"slug":1036,"type":16},"Debugging","debugging",{"name":1038,"slug":1039,"type":16},"Security","security",{"name":1041,"slug":1042,"type":16},"Testing","testing","2026-08-27T13:04:44.575925",{"slug":1045,"name":1045,"fn":1046,"description":1047,"org":1048,"tags":1049,"stars":26,"repoUrl":27,"updatedAt":1053},"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},[1050,1051,1052],{"name":1032,"slug":1033,"type":16},{"name":1038,"slug":1039,"type":16},{"name":1041,"slug":1042,"type":16},"2026-08-27T13:05:05.242264",{"slug":1055,"name":1055,"fn":1056,"description":1057,"org":1058,"tags":1059,"stars":26,"repoUrl":27,"updatedAt":1071},"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},[1060,1063,1066,1067,1070],{"name":1061,"slug":1062,"type":16},"Agents","agents",{"name":1064,"slug":1065,"type":16},"CI\u002FCD","ci-cd",{"name":24,"slug":25,"type":16},{"name":1068,"slug":1069,"type":16},"GitHub Actions","github-actions",{"name":1038,"slug":1039,"type":16},"2026-07-18T05:47:48.564744",{"slug":1073,"name":1073,"fn":1074,"description":1075,"org":1076,"tags":1077,"stars":26,"repoUrl":27,"updatedAt":1086},"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},[1078,1081,1082,1083],{"name":1079,"slug":1080,"type":16},"Audit","audit",{"name":24,"slug":25,"type":16},{"name":1038,"slug":1039,"type":16},{"name":1084,"slug":1085,"type":16},"Smart Contracts","smart-contracts","2026-08-21T03:32:34.227368",{"slug":1088,"name":1088,"fn":1089,"description":1090,"org":1091,"tags":1092,"stars":26,"repoUrl":27,"updatedAt":1098},"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},[1093,1096,1097],{"name":1094,"slug":1095,"type":16},"Python","python",{"name":1038,"slug":1039,"type":16},{"name":1041,"slug":1042,"type":16},"2026-08-27T13:04:51.552071",{"slug":1100,"name":1100,"fn":1101,"description":1102,"org":1103,"tags":1104,"stars":26,"repoUrl":27,"updatedAt":1108},"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},[1105,1106,1107],{"name":1079,"slug":1080,"type":16},{"name":24,"slug":25,"type":16},{"name":1038,"slug":1039,"type":16},"2026-08-21T03:32:38.432332",{"slug":1110,"name":1110,"fn":1111,"description":1112,"org":1113,"tags":1114,"stars":26,"repoUrl":27,"updatedAt":1121},"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},[1115,1118,1119,1120],{"name":1116,"slug":1117,"type":16},"Architecture","architecture",{"name":1079,"slug":1080,"type":16},{"name":24,"slug":25,"type":16},{"name":21,"slug":22,"type":16},"2026-08-08T03:55:04.309014",{"slug":1123,"name":1123,"fn":1124,"description":1125,"org":1126,"tags":1127,"stars":26,"repoUrl":27,"updatedAt":1132},"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},[1128,1129,1130,1131],{"name":1079,"slug":1080,"type":16},{"name":24,"slug":25,"type":16},{"name":21,"slug":22,"type":16},{"name":1038,"slug":1039,"type":16},"2026-08-27T13:05:06.207058",{"slug":1134,"name":1134,"fn":1135,"description":1136,"org":1137,"tags":1138,"stars":26,"repoUrl":27,"updatedAt":1144},"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},[1139,1140,1143],{"name":1079,"slug":1080,"type":16},{"name":1141,"slug":1142,"type":16},"CLI","cli",{"name":1038,"slug":1039,"type":16},"2026-07-17T06:05:33.198077",{"slug":1146,"name":1146,"fn":1147,"description":1148,"org":1149,"tags":1150,"stars":26,"repoUrl":27,"updatedAt":1155},"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},[1151,1152,1153,1154],{"name":1079,"slug":1080,"type":16},{"name":1032,"slug":1033,"type":16},{"name":24,"slug":25,"type":16},{"name":1038,"slug":1039,"type":16},"2026-08-27T13:04:50.663101",{"slug":1157,"name":1157,"fn":1158,"description":1159,"org":1160,"tags":1161,"stars":26,"repoUrl":27,"updatedAt":1166},"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},[1162,1163,1164,1165],{"name":1079,"slug":1080,"type":16},{"name":24,"slug":25,"type":16},{"name":1038,"slug":1039,"type":16},{"name":1084,"slug":1085,"type":16},"2026-08-21T03:32:39.232318",{"slug":1168,"name":1168,"fn":1169,"description":1170,"org":1171,"tags":1172,"stars":26,"repoUrl":27,"updatedAt":1179},"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},[1173,1174,1177,1178],{"name":21,"slug":22,"type":16},{"name":1175,"slug":1176,"type":16},"Rust","rust",{"name":1038,"slug":1039,"type":16},{"name":1041,"slug":1042,"type":16},"2026-08-27T13:04:42.229129",112,{"items":1182,"total":1230},[1183,1190,1196,1204,1211,1217,1223],{"slug":1026,"name":1026,"fn":1027,"description":1028,"org":1184,"tags":1185,"stars":26,"repoUrl":27,"updatedAt":1043},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1186,1187,1188,1189],{"name":1032,"slug":1033,"type":16},{"name":1035,"slug":1036,"type":16},{"name":1038,"slug":1039,"type":16},{"name":1041,"slug":1042,"type":16},{"slug":1045,"name":1045,"fn":1046,"description":1047,"org":1191,"tags":1192,"stars":26,"repoUrl":27,"updatedAt":1053},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1193,1194,1195],{"name":1032,"slug":1033,"type":16},{"name":1038,"slug":1039,"type":16},{"name":1041,"slug":1042,"type":16},{"slug":1055,"name":1055,"fn":1056,"description":1057,"org":1197,"tags":1198,"stars":26,"repoUrl":27,"updatedAt":1071},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1199,1200,1201,1202,1203],{"name":1061,"slug":1062,"type":16},{"name":1064,"slug":1065,"type":16},{"name":24,"slug":25,"type":16},{"name":1068,"slug":1069,"type":16},{"name":1038,"slug":1039,"type":16},{"slug":1073,"name":1073,"fn":1074,"description":1075,"org":1205,"tags":1206,"stars":26,"repoUrl":27,"updatedAt":1086},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1207,1208,1209,1210],{"name":1079,"slug":1080,"type":16},{"name":24,"slug":25,"type":16},{"name":1038,"slug":1039,"type":16},{"name":1084,"slug":1085,"type":16},{"slug":1088,"name":1088,"fn":1089,"description":1090,"org":1212,"tags":1213,"stars":26,"repoUrl":27,"updatedAt":1098},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1214,1215,1216],{"name":1094,"slug":1095,"type":16},{"name":1038,"slug":1039,"type":16},{"name":1041,"slug":1042,"type":16},{"slug":1100,"name":1100,"fn":1101,"description":1102,"org":1218,"tags":1219,"stars":26,"repoUrl":27,"updatedAt":1108},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1220,1221,1222],{"name":1079,"slug":1080,"type":16},{"name":24,"slug":25,"type":16},{"name":1038,"slug":1039,"type":16},{"slug":1110,"name":1110,"fn":1111,"description":1112,"org":1224,"tags":1225,"stars":26,"repoUrl":27,"updatedAt":1121},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1226,1227,1228,1229],{"name":1116,"slug":1117,"type":16},{"name":1079,"slug":1080,"type":16},{"name":24,"slug":25,"type":16},{"name":21,"slug":22,"type":16},78]