investigate-a-failure SKILL.md skillA
investigate-a-failure from joelhooks/rat-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add joelhooks/rat-stack/investigate-a-failure@git:20261023.b93dadfPins git:20261023.b93dadf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- joelhooks/rat-stack
- Path
skills/investigate-a-failure/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261023.b93dadf, committed Oct 23, 2026
- First version recorded
- Oct 10, 2026
- Size
- 4,746 bytes
- Repository stars
- 216
- License
- MIT
Find the cause of a crash, wrong output, flaky test, or slow run with evidence, fix it at its source, and leave a notebook a person can learn from. Use when something fails intermittently, when the first fix idea is "raise the timeout" or "swap the version", or when asked "why does this break" or "make this stable".
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
# Investigate a failure Find why something fails before you change it. A fix chosen before the cause is known can hide the failure without removing it. Swapping a version, image, or provider until the symptom stops teaches nothing. The next failure stays as mysterious as this one. Read `AGENTS.md` first. Then read these leaves: - `skills/rat-stack-mode/principles/find-the-cause-first.md` - `skills/rat-stack-mode/principles/rebuild-what-you-run.md` - `skills/rat-stack-mode/principles/measure-real-limits.md` - `skills/rat-stack-mode/principles/keep-execution-receipts.md` When the failure is a timeout, a pool wait, or a reset, join it to the provider calls in flight. Then read [durability](/skills/durability) before you raise a limit. ## Terms used here - **Repro:** a script that makes the failure happen on demand, at a known rate. - **Hypothesis:** one testable claim about the cause. It stays a hypothesis until an experiment proves it. - **Probe:** temporary instrumentation that checks a hypothesis. It stops the run cleanly, with the values it saw, before the failure happens. …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_id2bgp4ltoabb4lj/4099985a5fc929cecf6e4cb23082e7532f0de8bdb830c47825989c454a0a65ab.json
Then /plugin install investigate-a-failure@markdownregistry-id2bgp4ltoabb4lj in Claude Code. It installs git:20261023.b93dadf, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add joelhooks/rat-stack/investigate-a-failure@sha256:4099985a5fc929ceThe line at the top of this page pins the label git:20261023.b93dadf, 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.
[](https://markdownregistry.com/a/art_id2bgp4ltoabb4lj)
3 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in joelhooks/rat-stack/investigate-a-failure 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 investigate-a-failure from somewhere else? Ask it: where did my investigate-a-failure 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 2 versions of this file, between Oct 10, 2026 and Oct 23, 2026, about one every 13 days.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261023.b93dadf latest | 2026-10-23 | b93dadf | 4,746 B | A | view · diff |
| git:20261010.0d43dfc | 2026-10-10 | 0d43dfc | 4,579 B | A | view |
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.
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.
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.
Installed this file, say at .claude/skills/investigate-a-failure/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
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
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4746 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
joelhooks/rat-stack · 216 stars · license MIT · pushed 2026-11-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_id2bgp4ltoabb4lj GET https://markdownregistry.com/api/v1/resolve?ref=joelhooks/rat-stack/investigate-a-failure GET https://markdownregistry.com/api/v1/blob/4099985a5fc929cecf6e4cb23082e7532f0de8bdb830c47825989c454a0a65ab
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.