snapshot
Skill0 starsChanged 4 months agoMITView on GitHub
Produce a short, plain-English status of the whole program - what's solid, what's new since the canonical state, honest negatives/obstructions, and open/next - using fast parallel reads. Explains results in lay terms, never just citing gate names. Use when the user says "/snapshot", "where do things stand", or "current status".
9 other projects use a version of this.
Adopted by
Most recently taken up by
- XyndoX/agent-skillstheir own version, first seen Oct 20, 2026
- boostsecurityio/poutinetheir own version, first seen Oct 8, 2026
- IvanSkainet/arena-agenttheir own version, first seen Aug 13, 2026
- ewebdzine/claude-code-time-trackertheir own version, first seen Jul 26, 2026
- matvej-melikhov/karpathy-llm-wikitheir own version, first seen May 22, 2026
- berch-t/Kopern-OStheir own version, first seen May 14, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- boostsecurityio/poutine★ 535same name
- sanghun0724/cmux-claude-skills★ 33same name
- IvanSkainet/arena-agent★ 8same name
- matvej-melikhov/karpathy-llm-wiki★ 2same name
- Pedro-B-Siqueira/snapshot★ 1same name
- arbones/claude-skills★ 0same name
- berch-t/Kopern-OS★ 0same name
- ewebdzine/claude-code-time-tracker★ 0same name
- XyndoX/agent-skills★ 0same 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- fleet/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/atlas.mdcCursor rule
- add-repoSkill
- atlas-setupSkill
- councilSkill
- mediateSkill
- onboardSkill
- optimizeSkill
- registry-syncSkill
- researchSkill
- sync-repo-knowledgeSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Read the canonical surfaces first and note their dates:
“Common” is measured: kept by at least 6 in 10 of the 5 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
/snapshot - plain-English status of the program
Goal: a short, simple-English briefing of the latest state. The reader may not be technical - explain what results mean, don't just cite them.
Step 1 - Orient (fast, yourself)
Read the canonical surfaces first and note their dates:
CURRENT_STATE.md- live claims, withdrawn register, adoptions, open work.Home.md- the topic index. Then find what changed after the canonical state's date (recent commits / newest files) - those are the freshest results that may not be folded in yet. Flag them as not-yet-canonical.
Step 2 - Fan out (parallel reads)
Launch read-only agents concurrently, each with a tight scope (experiments, topic pages, and each
repo listed in REPOS.md), each returning a plain-English summary: what was tested, the result,
and whether it's a positive, a negative, an obstruction, or still open. Scale the fleet to the ask.
Step 3 - Synthesize
Write the briefing:
- Headline - the single most important state right now.
- What's solid - cleared-the-checklist claims, in lay terms (what it means).
- What's new since canonical state - clearly marked if not yet folded in.
- Honest negatives & obstructions - reported plainly, never buried.
- Open / next - the live questions.
Rules: plain language (gloss any term on first use); never repeat a withdrawn number as if live; date the snapshot and name sources; separate "proven / replicated / toy-scope / open" honestly.
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.

