Investigate a bug or broken behavior through hypothesis-driven root cause analysis and report what is wrong without jumping straight to a fix. Use when something is failing or behaving unexpectedly.
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
Find the root cause before proposing a fix.
Rules:
- Do not make code changes unless the user explicitly approves diagnostic logging.
- Do not guess. Support every conclusion with evidence from code, logs, or commands.
Workflow:
1. Clarify expected behavior, observed behavior, and reproduction steps if missing.
2. Classify the bug type early: compile, logic, race, state, integration, environment, or UI.
3. Write 3-5 ranked hypotheses before reading deeply.
4. Test those hypotheses by tracing the relevant code and recent history.
5. Compare broken and working paths when possible.
6. If the cause is still unclear, propose targeted logging and explain exactly why.
7. Report the root cause, confidence level, affected files, likely introduction point, and what needs to change.
Red flags:
- proposing a fix before confirming the cause
- pursuing the same failed theory repeatedly
- analyzing code unrelated to the symptoms
The line at the top of this page pins the label git:20260924.17234b5, 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.
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 (1185 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
greenfield-inc/pane · 575 stars · license a license file GitHub does not identify · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_r4ql5qjjv7myocfc
GET https://markdownregistry.com/api/v1/resolve?ref=greenfield-inc/pane/investigate
GET https://markdownregistry.com/api/v1/blob/b0199e594f142eaf17a44c193de78e04463212d7b2cdc9a858796d0d51d1e5e6
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.
greenfield-inc/pane · main/src/services/paneChatBundle/skills/babysit-pr/SKILL.md · Use after a pull request is open to watch its CI and review-bot comments until it is ready. Fixes real findings…
greenfield-inc/pane · main/src/services/paneChatBundle/skills/brief/SKILL.md · Use when a problem, idea, or change of intent is worth capturing as a long-form page, or the person asks to write it…
greenfield-inc/pane · main/src/services/paneChatBundle/skills/bug-intake/SKILL.md · Use when the person reports broken behaviour or starts a session to file a bug. Reproduces and reports. Never fixes.
greenfield-inc/pane · main/src/services/paneChatBundle/skills/codebase-design/SKILL.md · Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…
greenfield-inc/pane · main/src/services/paneChatBundle/skills/cold-read/SKILL.md · Have a fresh agent walk through something with zero context (a PR body, a landing page, a document, a process…
greenfield-inc/pane · main/src/services/paneChatBundle/skills/create-ticket/SKILL.md · Capture work and evolving intent during discussion as one or more GitHub tickets, Grain briefs, or both. Use for ticket…
greenfield-inc/pane · main/src/services/paneChatBundle/skills/discussion/SKILL.md · Have an interactive discussion about a topic, approach, feature, or bug without making code changes. Researches the…
greenfield-inc/pane · main/src/services/paneChatBundle/skills/eli5/SKILL.md · Teach an unfamiliar topic from first principles with a picture-first HTML explanation, saved in Grain when connected…
greenfield-inc/pane · main/src/services/paneChatBundle/skills/excalidraw-pr-diagrams/SKILL.md · Create Excalidraw diagram JSON files and PR visual overviews that make visual arguments. Use when the user wants to…
dcouple/pane · main/src/services/paneChatBundle/skills/investigate/SKILL.md · Investigate a bug or broken behavior through hypothesis-driven root cause analysis and report what is wrong without…
testdouble/han · han-coding/skills/investigate/SKILL.md · Evidence-based investigation of issues, bugs, API calls, integrations, and other aspects of software development that…
borda/ai-rig · plugins/cc_foundry/skills/investigate/SKILL.md · Systematic diagnosis for unknown failures — local environment, tool setup, CI vs local divergence, hook misbehavior…
