Borrowing it
Nothing to install: this file belongs to ahonn/dotfiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ahonn/dotfiles/master/.claude/skills/investigate/SKILL.mdgit clone --depth 1 https://github.com/ahonn/dotfilesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ahonn/dotfiles/investigate)<a href="https://agentmods.dev/skills/ahonn/dotfiles/investigate"><img src="https://agentmods.dev/badge/skills/ahonn/dotfiles/investigate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ahonn/dotfiles/investigate"><img src="https://agentmods.dev/badge/skills/ahonn/dotfiles/investigate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00777 |
| Opus 5.5 | $0.00009 | $0.00311 |
| Sonnet 5.5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
investigate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
Use evidence to explain the failure before changing behavior. Scale investigation to uncertainty and impact; a clear stack trace may need only a short trace, while intermittent failures may need instrumentation.
Follow the global AGENTS.md for authorization and test mode. Continue work already authorized by the session. Do not impose additional approval gates, a fixed retry limit, or mandatory test-first development.
Collect evidence and reproduce
- Read the complete error and relevant execution path. Identify the expected and observed behavior.
- Establish when the failure began and whether it depends on inputs, timing, environment, or recent changes.
- Reproduce with the smallest relevant command, test, or manual sequence. For intermittent failures, record the conditions and frequency.
- If reproduction is unavailable, use logs, traces, and code evidence to narrow the cause. State the remaining uncertainty; do not claim verification from inspection alone.
- Inspect actual OS, runtime, SDK, or dependency versions when they affect the hypothesis. Do not diagnose version problems from memory.
- For unavailable tools or external services, inspect the failure enough to choose a useful next step. Use an equivalent authorized fallback when appropriate; do not turn an unrelated tool outage into a separate repair project.
Narrow the cause
Trace the failing value or operation across boundaries. Compare working and failing cases, and vary one relevant factor at a time when practical.
| Pattern | Evidence to seek |
|---|---|
| Race condition | Timing-dependent shared state, missing sequencing, stale async results |
| Null propagation | The earliest point an expected value becomes absent |
| State corruption | Mutation, cache invalidation, stale closures, ownership violations |
| Integration failure | Contract mismatch, version skew, differing configuration |
| Stale cache | Cached content or build artifacts that differ from the current source |
| Test pollution | Shared state, missing cleanup, order-dependent behavior |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 20d ago Changed · -143 lines · -33 tokens per session f6fdc717c693
- 1mo ago First seen · 196 lines · 56 tokens per session scan A 203857c86a37
investigate is a skill published in the GitHub repository ahonn/dotfiles (63 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 777 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
save-debug-experience
Record a debugging session's findings into a timestamped markdown file under debugexperience/. Captures problem, root cause, solution, and key learnings in a structured, reusable format. Use when: you've just resolved a non-obvious bug, found an undocumented edge case, encountered an issue that took multiple attempts…
diagnose-ci
Investigate failing REMOTE CI runs on GitHub Actions: find the failed run, pull the failed-step logs with gh, identify the root cause (compile error, test failure, lint, missing secret, timeout), and recommend a fix. Read-only: it does not commit, push, or edit. Use when CI is red, a GitHub Actions run failed, or the…
triage-dotfiles-env
Playbook of known failure modes in this dotfiles stack: pipx "bad interpreter" after Python rebuilds, gpg commit-signing failures, direnv/nix shellHook running bash instead of zsh, Powerlevel10k instant-prompt warnings, and Neovim plugin errors from removed Lua APIs. Use when a shell startup error, git signing…
fix-and-retry
Diagnose a failing CI run, apply the code fix, commit it, push, and watch the re-run until it passes or fails -- the full fix-and-retry loop in one shot. Use after a pipeline fails and the user says "fix it and retry", "fix the CI and push", or "make CI green". Do NOT use for a read-only investigation that stops at a…
diagnose-runtime
Triage LOCAL runtime failures on your own machine: crashes and errors, hangs and deadlocks, slowness and high CPU/memory, and hardware/serial/USB issues. Method: reproduce, isolate (bisect, log, strace/dtruss, sample), form a hypothesis, verify the fix holds. Read-mostly: it inspects processes and logs, it does not…
coding
Principles for writing, changing, and testing code, covering readability at every scale, abstraction and naming, interfaces, comments and documentation, tests as maintained code, and standards of evidence for claims about code behavior.