bug-hunt SKILL.md skillA

bug-hunt from chrisallenlane/claude-swe-workflows is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add chrisallenlane/claude-swe-workflows/bug-hunt@git:20261116.75ffff6

Pins git:20261116.75ffff6 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
chrisallenlane/claude-swe-workflows
Path
skills/bug-hunt/SKILL.md
Versions recorded
5
Latest version
git:20261116.75ffff6, committed Nov 16, 2026
First version recorded
Oct 30, 2026
Size
11,099 bytes
Repository stars
21
License
MIT

Proactive bug hunting. Assesses where bugs likely hide, confirms each finding with a reproducing test, and iterates until nothing is found above a severity floor. Advisory by default; creates tickets or fixes via /implement only when authorized.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Bug Hunt — Find Bugs Before Users Do

Hunts for bugs nobody knows about yet. An assessor works out where bugs are likely to hide by cross-referencing change history (complexity × churn hotspots, fix density, change coupling), coverage gaps, and structural risk; focused hunters then probe each hotspot and write a reproducing test for every suspected bug. No speculative reports: a finding without a failing test is a suspicion, and is labeled as one.

The user states intent once. The skill then hunts round after round until a round confirms nothing at or above the severity floor — and, if given the authority, tickets what it finds and fixes it via `/implement` between rounds.

## Philosophy

**Evidence, not opinion.** Every confirmed bug has a reproducing test that encodes the correct behavior and fails against the current code. That test is the finding's proof, the ticket's acceptance criterion, and the fix's verification.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ua3fiomld6imzzfg/e59a906c2e1abc83da6ddb78af48ffdaa0225d1dbe779b34966314537f3ebe1f.json

Then /plugin install bug-hunt@markdownregistry-ua3fiomld6imzzfg in Claude Code. It installs git:20261116.75ffff6, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add chrisallenlane/claude-swe-workflows/bug-hunt@sha256:e59a906c2e1abc83

The line at the top of this page pins the label git:20261116.75ffff6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ua3fiomld6imzzfg.svg)](https://markdownregistry.com/a/art_ua3fiomld6imzzfg)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in chrisallenlane/claude-swe-workflows/bug-hunt since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of bug-hunt from somewhere else? Ask it: where did my bug-hunt come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Oct 30, 2026 and Nov 16, 2026, about one every 4 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261116.75ffff6 latest2026-11-16 75ffff6 11,099 BA view · diff
git:20261116.e39effb2026-11-16 e39effb 11,363 BA view · diff
git:20261116.0b1f2682026-11-16 0b1f268 11,352 BA view · diff
git:20261030.96bb2f22026-10-30 96bb2f2 11,253 BA view · diff
git:20261030.75c2b6e2026-10-30 75c2b6e 11,285 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11099 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

chrisallenlane/claude-swe-workflows · 21 stars · license MIT · pushed 2026-11-17 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_ua3fiomld6imzzfg
GET https://markdownregistry.com/api/v1/resolve?ref=chrisallenlane/claude-swe-workflows/bug-hunt
GET https://markdownregistry.com/api/v1/blob/e59a906c2e1abc83da6ddb78af48ffdaa0225d1dbe779b34966314537f3ebe1f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from chrisallenlane/claude-swe-workflows

CLAUDE.md CLAUDE.md file
chrisallenlane/claude-swe-workflows · CLAUDE.md
git:20261116.9909590 · audit A · 21 stars
bug-fix SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/bug-fix/SKILL.md · Diagnosis-first bug fixing with test-driven reproduction, root-cause analysis, and a targeted fix plus regression test…
git:20261116.75ffff6 · audit A · 21 stars
implement SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/implement/SKILL.md · Implements a ticket, a batch, or an open-ended goal end to end, choosing agents and reviews by judgment over a fixed…
git:20261116.75ffff6 · audit A · 21 stars
pre-compact SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/pre-compact/SKILL.md · Pre-compaction housekeeping. Updates persistent memory, checks git hygiene and trash, produces an SBAR with a go/no-go…
git:20261116.75ffff6 · audit A · 21 stars
refactor SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/refactor/SKILL.md · Simplification-first codebase redesign (Musk's five steps), with behavior pinned by a differential oracle against the…
git:20261116.75ffff6 · audit A · 21 stars
release SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/release/SKILL.md · Cuts a project release. Discovers the release procedure, runs /review-release as preflight, proposes a version bump…
git:20261116.75ffff6 · audit A · 21 stars
review-a11y SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/review-a11y/SKILL.md · Accessibility audit. Dispatches an accessibility auditor to identify WCAG conformance gaps, prioritize by user impact…
git:20261116.ba42984 · audit A · 21 stars
review-perf SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/review-perf/SKILL.md · Performance review. Detects project type and dispatches compute and/or web performance reviewers. Advisory only — no…
git:20261116.afefe92 · audit A · 21 stars
review-release SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/review-release/SKILL.md · Pre-release readiness review. Checks for debug artifacts, version mismatches, changelog gaps, git hygiene issues…
git:20261116.75ffff6 · audit A · 21 stars
review-repo SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/review-repo/SKILL.md · Whole-repository review. With no focus, maps where to engage or tread carefully, including tech-debt hotspots. Focuses…
git:20261116.75ffff6 · audit A · 21 stars
review-security SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/review-security/SKILL.md · White-box security audit. Independent blue-team and red-team passes are synthesized into targets for focused red-team…
git:20261116.75ffff6 · audit A · 21 stars
review-test SKILL.md skill
chrisallenlane/claude-swe-workflows · skills/review-test/SKILL.md · Test suite review covering unit, integration, E2E (browser), and fuzz coverage plus test quality. Advisory only…
git:20261116.75ffff6 · audit A · 21 stars

Every file in chrisallenlane/claude-swe-workflows

Other files named bug-hunt

bug-hunt SKILL.md skill
escoffier-labs/brigade · registry/skills/bug-hunt/SKILL.md · Use when asked to find bugs, hunt for correctness issues, sweep a codebase for defects, or verify a repo behaves as…
git:20261104.d46ce4d · audit A · 83 stars
bug-hunt SKILL.md skill
yeaight7/agent-powerups · plugins/debugging-diagnostics/skills/bug-hunt/SKILL.md · Use when reproducing, isolating, and fixing a bug with the smallest safe change.
git:20260502.7e2d1d5 · audit A · 9 stars
bug-hunt SKILL.md skill
yeaight7/agent-powerups · skills/bug-hunt/SKILL.md · Use when reproducing, isolating, and fixing a bug with the smallest safe change.
git:20260427.9e3c858 · audit A · 9 stars
bug-hunt SKILL.md skill
escoffier-labs/skillet · skillet/skills/bug-hunt/SKILL.md · Use when asked to find bugs, hunt for correctness issues, sweep a codebase for defects, or verify a repo behaves as…
v0.1.0 · audit A · 4 stars
bug-hunt SKILL.md skill
coderperseus/skills · skills/bug-hunt/SKILL.md · Systematic root-cause debugging for software bugs (frontend, backend, mobile). Use when the user reports a symptom that…
git:20260525.95477a8 · audit A · 2 stars

Browse by kind, by grade A, or by owner.