inspect
Skill4 starsChanged 24 days agoMITView on GitHub
Show where this conversation's tokens went: usage by kind and by model, the subagents by agent type and model, context growth, the cache, the biggest tool outputs, searches (their chains and big results, and whether a code index was seen), repeated reads, each hook's times by event and source, what the guard caught, and the Advisor's consultations when there were any. Numbers only, each with its source.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- matthewdonsemail-lab/logtheir own version, first seen Nov 15, 2026
- sanityops-org/sanityops-frameworktheir own version, first seen Nov 4, 2026
- cyrilichti/agent-workflowstheir own version, first seen Oct 17, 2026
- chalk-lab/Mooncake.jltheir own version, first seen Oct 8, 2026
- saleh-alhaddad/itqan-engineeringtheir own version, first seen Sep 29, 2026
- ZeeshanSultan/DocGovtheir own version, first seen Sep 13, 2026
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- chalk-lab/Mooncake.jl★ 413same name
- Arman-Kudaibergenov/1c-ai-development-kit★ 163same name
- bluzir/claude-code-design★ 102same name
- matthewdonsemail-lab/log★ 63same name
- NakaokaRei/swift-mcp-gui★ 61same name
- howardpen9/cc-inspect★ 17same name
- saleh-alhaddad/itqan-engineering★ 10same name
- HaipingShi/coderail★ 8same name
- cyrilichti/agent-workflows★ 3same name
- sanityops-org/sanityops-framework★ 3same name
5 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.
In this repository3 other files it gives its agents.
- checkpointSkill
- doctorSkill
- manageSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
If the user gave an argument ($ARGUMENTS), run ${CLAUDE_PLUGIN_ROOT}/bin/longhaul inspect "$ARGUMENTS" instead and show that.
“Common” is measured: kept by at least 6 in 10 of the 13 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
The report below is Longhaul's reading of this conversation's own transcript, its subagents' transcripts, the ledger, the guard's record and the Advisor experiment's trace. It holds numbers, model names, tool names and file paths only; never message text or tool output. Each heading names where its numbers came from and how sure they are: measured, counted, inferred or estimated.
!${CLAUDE_PLUGIN_ROOT}/bin/longhaul inspect "${CLAUDE_SESSION_ID}"
Show the report to the user as it is, in a code block, without changing or
rounding any number. If it says no transcript was found, say so and show
the message: the conversation may be too new for Claude Code to have
written its file, or Longhaul's folder may be elsewhere (LONGHAUL_HOME).
If the user gave an argument ($ARGUMENTS), run
${CLAUDE_PLUGIN_ROOT}/bin/longhaul inspect "$ARGUMENTS" instead and show
that.
The report may name an install command; show it, take no install step.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.