Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add motlin/claude-code-plugins --skill investigation-reportgit clone --depth 1 https://github.com/motlin/claude-code-pluginsWrote 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/motlin/claude-code-plugins/investigation-report)<a href="https://agentmods.dev/skills/motlin/claude-code-plugins/investigation-report"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/investigation-report/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/motlin/claude-code-plugins/investigation-report"><img src="https://agentmods.dev/badge/skills/motlin/claude-code-plugins/investigation-report.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 | $0.00069 | $0.00612 |
| Opus 5.5 | $0.00028 | $0.00245 |
| Sonnet 5.5 | $0.00014 | $0.00122 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
investigation-report 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 22d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command-Line Investigation Report
Produce a chronological command log as one HTML page: what you ran, what it printed, and enough reasoning that the reader could rerun it and understand every flag. The goal is teaching, not a status update.
Before designing it, read Red Blob Games' Making of: Circle drawing tutorial as the quality benchmark for teaching through an HTML page.
Structure it as a chronological command log
Walk the investigation in the order it happened, including dead ends, wrong hypotheses, and the commands that disproved them. Do not sanitize it into a clean after-the-fact story. Each step is the command, its real output, one line of why you ran it, and, only where the evidence changed your conclusion, a short "changed my mind" note. Make those turning points stand out; they are the spine of the story.
Show real commands and real output
- Reproduce commands verbatim. Never clean up flags or show a command you did not run.
- Paste actual output, trimmed to what matters, and mark every cut visibly (e.g.
... ~60 more lines ...). - For commands that revealed nothing useful, skip the output and just note what you ran and why.
Explain unfamiliar commands and flags
- For non-obvious commands, add a breakdown with one plain-language row per flag.
- Split fused flags:
-nrk3is-n -r -k3. - Explain a pipeline inside-out, like nested parentheses: command substitution first, then the tools it feeds.
- For a likely unfamiliar tool (e.g.
pgrep), add a short "what is X": the basics, the flags used here, and its closest sibling (pgrep/pkill). - Let the reader's questions drive depth: skip what they know, expand what they ask about.
Keep commentary out
Cut editorializing, "lessons learned" summaries, and meta-commentary about method unless asked. Prefer "here is what I did" over "here is what you should learn."
End with a command reference
Close with a compact table mapping question → command → what to read from the output.
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.
- 22d ago Changed · -7 lines a37137ac0091
- 29d ago Changed · +6 lines 42609c7435ef
- 1mo ago First seen · 46 lines · 69 tokens per session scan A 7cf62c35e654
investigation-report is a skill published in the GitHub repository motlin/claude-code-plugins (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 612 once invoked, about $0.0003 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 2026-09-04.
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.
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…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…