observatory
Skill6 starsChanged 27 days agoMITView on GitHub
Show the owner what the agents did in this project — every tool call, changed file, notable command, web and MCP use, what the guard and the sentinel refused or hid, permission denials, token use and what it cost (prompt cache, rebuilds and their causes) — read from Claude Code's own session transcripts by tools/observe.py and explained in Georgian. Use when the owner asks what an agent did, wants an audit or the "AI observatory" view, asks about security events, or before /session-close.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jgravelle/jcodemunch-mcptheir own version, first seen Sep 4, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- jgravelle/jcodemunch-mcp★ 2.9ksame name
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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adrSkill
- approveSkill
- feature-planSkill
- intentSkill
- orchestrateSkill
- reflectSkill
- session-closeSkill
- specSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 10
Run bash .claude/hooks/py.sh tools/observe.py report --session ${CLAUDE_SESSION_ID} — or, with the owner's argument, a session id prefix or …
- Distinctive: line 20
Never paste a tool's output or any secret — the report is already redacted.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/observatory — what the agents did, in Georgian
- Run
bash .claude/hooks/py.sh tools/observe.py report --session ${CLAUDE_SESSION_ID}— or, with the owner's argument, a session id prefix orlast; for "the last N days" runbash .claude/hooks/py.sh tools/observe.py sessions --days N. - Exit 2 (
OBSERVE INCONCLUSIVE) means nothing was proved — say so plainly; never present it as "nothing happened". - Explain to the owner in 2–4 connected Georgian paragraphs: how much was done; which files changed and why (name the
task
D-NNNor plan task it served); every line under "ბრძანებები, რომლებსაც ყურადღება სჭირდება"; every security event —GUARD[..](what was refused and why),SENTINEL[R1/R2](a key appeared — where, and that the owner should rotate it),SENTINEL[I1/I2](suspicious outside text); permission denials; token use; and the "ქეში და ხარჯი" section — the API-price yardstick (a measure of the subscription limits, not a bill), the share read from the cache, and every rebuild with its cause; for an avoidable one (a long pause, a restart, a model switch) name the habit that avoids it ([[process]] §5, ADR-0010).--session allmeasures every session of the project. - Never paste a tool's output or any secret — the report is already redacted. If something looks wrong (a changed file no task explains, a refused attempt that repeats), say so and propose the next step; do not fix anything here.
- State the limits honestly: the report sees only Claude Code sessions of this project folder (not Codex, not other
tools); a file changed by a shell command is listed only when Claude Code tracked it; transcripts are deleted after
about 30 days, which is why
/session-closekeeps the brief line in the episode (ADR-0007).
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.

