why
Skill46 starsChanged 31 days agoMITView on GitHub
Forensic audit of the user's most recent Claude Code session. Returns total spend, output ratio, duplicate file reads, idle context after auto-compact, the largest requests (with the tool call each one made), and an estimate of what Sipcode would have RECOVERED if optimizers were active. Use when the user asks "where did my tokens go?", "audit my last session", "why was that session so expensive?", or any forensic question about a past Claude Code session.
112 other projects use a version of this.
Adopted by
Most recently taken up by
- Yeachan-Heo/oh-my-claude-sisyphustheir own version, first seen Nov 8, 2026
- Loner1024/skillstheir own version, first seen Nov 8, 2026
- caidanw/skillstheir own version, first seen Nov 8, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 8, 2026
- endqwerty/endstacktheir own version, first seen Nov 8, 2026
- tristanphvn/keeltheir own version, first seen Nov 8, 2026
Used with
Projects with it also use addskill, apply-firmware and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
- ryanportfolioSkill
apply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +10 more from ryanportfolio
Other versions112 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 112
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- backnotprop/pstack★ 3.8ksame name
- moeru-ai/xsai★ 667same name
- jtaroreh/agystack★ 128same name
- uzairansaruzi/p3-stack★ 126same name
- Dimon94/dverity★ 107same name
- Dimon94/skills★ 107same name
- dsebban/skills★ 71same name
- valentynkit/jev-belay★ 38same name
102 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 106 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Call the sipcode:audit_latest_session MCP tool to produce a forensic report of the user's most recent Claude Code session.
- Very specific: line 9
If the user provides a session ID prefix (e.g., "audit session 3bca35e2"), pass it as the session_id argument.
- Distinctive: line 11
When presenting the result:
- Very specific: line 14
If you mention the largest requests (topExpensive), say each row's tokens are the whole request's (mostly the context sent with it), not …
- Distinctive: line 16
If the session is unusually large (> $10), call that out.
- Distinctive: line 18
Do NOT extrapolate the single-session savings across many sessions.
“Common” is measured: kept by at least 6 in 10 of the 106 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Sipcode why (session forensics)
Call the sipcode:audit_latest_session MCP tool to produce a forensic report of the user's most recent Claude Code session.
If the user provides a session ID prefix (e.g., "audit session 3bca35e2"), pass it as the session_id argument. Otherwise, omit and the tool will pick the most recent session across all projects.
When presenting the result:
- Lead with the output ratio (
punchline.outputRatioPct: output, meaning the text, code and reasoning the model wrote, as a share of the tokens not read from cache). The other tokens are the context sent with each request (the one-liner says how much of it was read from cache, which costs a fraction of the input price); do not call them exploration or waste. - Surface the top 3 leaks with their dollar cost.
- If you mention the largest requests (
topExpensive), say each row's tokens are the whole request's (mostly the context sent with it), not what the tool call cost. - The "Sipcode estimates ~X tokens were RECOVERABLE" line is potential, not realized. Only realized after
sipcode rules --install+ new sessions +sipcode impact. Be explicit about this when relaying the number. - If the session is unusually large (> $10), call that out.
Do NOT extrapolate the single-session savings across many sessions. Each session is its own forensic snapshot.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.