Borrowing it
Nothing to install: this file belongs to tom5610/llm-wiki. 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/tom5610/llm-wiki/main/.claude/skills/investigate/SKILL.mdgit clone --depth 1 https://github.com/tom5610/llm-wikiWrote 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/tom5610/llm-wiki/investigate)<a href="https://agentmods.dev/skills/tom5610/llm-wiki/investigate"><img src="https://agentmods.dev/badge/skills/tom5610/llm-wiki/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/tom5610/llm-wiki/investigate"><img src="https://agentmods.dev/badge/skills/tom5610/llm-wiki/investigate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00106 | $0.01276 |
| Opus 5 | $0.00053 | $0.00638 |
| Sonnet 5 | $0.00021 | $0.00255 |
| Haiku 4.5 | $0.00011 | $0.00128 |
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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate workflow
Perform root cause analysis on a development issue. Use $ARGUMENTS as the error message, problem description, or context if provided (e.g., /investigate Failed to load hooks from hooks.json: expected record, received undefined).
Phase 1: Gather Context
The goal is to understand the problem deeply before jumping to conclusions. Shallow investigation leads to wrong fixes.
-
Parse the input. Extract from
$ARGUMENTSor the conversation:- Error messages, codes, and stack traces
- Which command or operation triggered it
- File paths mentioned in the error
- Any context the user provided about what they were doing
-
Read the relevant files. Start with files directly mentioned in the error, then fan out:
- The file(s) where the error originates
- Config files that govern the failing system (e.g.,
plugin.json,settings.json,pyproject.toml) - Related files that might define the expected schema or format
- Recent git changes if the error is a regression (
git log --oneline -10,git diff HEAD~3)
-
Research the expected behavior. This is the critical step most debugging skips — understanding what should happen before diagnosing what went wrong:
- Read documentation, schemas, or source code that defines the correct format/behavior
- Check for examples of the correct pattern elsewhere in the project or in reference implementations
- If the error involves a third-party tool or framework, use available resources (docs, existing working configs in the project) to understand the contract
-
If the problem is unclear, ask. Use the
AskUserQuestiontool to narrow down before proceeding — but only when genuinely ambiguous. Don't ask about things you can determine by reading code.- "When did this start happening?" / "Did it work before?"
- "Which command produces this error?"
- "Are there other symptoms or related errors?"
Phase 2: Analyze Root Cause(s)
Think through the problem systematically. Most errors have a single root cause, but some have contributing factors worth surfacing.
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.
- 9d ago First seen · 83 lines · 106 tokens per session scan A c5ffcbaf392a
investigate is a skill published in the GitHub repository tom5610/llm-wiki (2 stars, last pushed 4mo ago), licensed MIT. It adds 106 tokens to every session and 1,276 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.