Borrowing it
Nothing to install: this file belongs to tatargabor/set-copilot. 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/tatargabor/set-copilot/master/.claude/skills/set/forensics/SKILL.mdgit clone --depth 1 https://github.com/tatargabor/set-copilotWrote 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/tatargabor/set-copilot/forensics)<a href="https://agentmods.dev/skills/tatargabor/set-copilot/forensics"><img src="https://agentmods.dev/badge/skills/tatargabor/set-copilot/forensics.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00914 |
| Opus 5 | $0.00025 | $0.00457 |
| Sonnet 5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
set:forensics 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 yesterday.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/set:forensics — Run forensics
Triage what failed in a completed orchestration run using filtered views over Claude Code session transcripts and orchestration logs.
WARNING — never read raw session jsonl files unbounded. A single session jsonl can exceed 300 KB and a run typically has 50+ sessions. Always go through the CLI's filtered views first; only fall back to raw Read on a specific line range when the CLI has narrowed the suspect.
Triage order
Always follow this sequence:
-
set-run-logs <run-id> discover— confirm the scope of resolved sources. Verify the main session dir and every-wt-<change>worktree dir was found, plus the orchestration dir. -
set-run-logs <run-id> digest— get the error map. Aggregates tool errors, non-zero bash exits, stop-reason anomalies, user interrupts, permission denials, and crash suspects across every session. Output is grouped by change → session → tool with snippets. -
set-run-logs <run-id> session <uuid> --errors-only— for each suspect session in the digest, view its tool-call timeline filtered to errors. Use the short UUID prefix (≥6 chars) from the digest. Only AFTER you've narrowed via this view should you read raw jsonl. -
set-run-logs <run-id> grep <pattern>— targeted probe for a specific error signature across all sessions. Emits ONLY the matchingmessage.contenttext (not raw jsonl lines), so it's safe to use in agent context. Default cap is 50 matches — pass--limitto raise. -
set-run-logs <run-id> orchestration— cross-reference timing. Shows per-change dispatch counts, last gate status, terminal status, gate-outcome counts. Use this to map a suspect session back to its orchestration timeline (when it dispatched, which gate triggered, what the terminal status was). -
Raw jsonl as last resort. If the CLI's filtered views still leave a question unanswered, locate the specific jsonl from
discoveroutput andReadonly the line range you need. NeverReada session jsonl without an offset/limit.
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.
- yesterday First seen · 60 lines · 50 tokens per session scan A dc109012770e
set:forensics is a skill published in the GitHub repository tatargabor/set-copilot (2 stars, last pushed 13d ago), licensed MIT. It adds 50 tokens to every session and 914 once invoked, about $0.0003 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 2026-09-04.
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.
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
Orchestrates Volcengine Cloud Detect (云拨测) false-alarm reduction for failing periodic-task dial points. Use for scheduled task scans, retrying failed nodes, control-testing node health, distinguishing real target outages from broken dial points, and suggesting same-type LastMile/IDC/Private replacement nodes. Runs the…