agent-checkpoint / adapters
CLAUDE.md3 starsChanged 39 days agoMITView on GitHub
In this repository3 other files it gives its agents.
- adapters/AGENTS.mdAGENTS.md
- adapters/copilot-instructions.mdCopilot instructions
- agent-checkpointSkill
The file
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Before modifying or rewriting any existing file:
- Very specific: line 6
ALWAYS archive the exact pre-edit file into .snapshots/<filepath>/v<OLD_VERSION>.<ext>.
- Very specific: line 10
Update sharded index at .snapshots/<filepath>/manifest.json.
- Very specific: line 12
Never re-read historical REVISION_LOG.md entries into context.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md 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
AGENT-CHECKPOINT PROTOCOL v2.0 (Claude Code)
Place this file as CLAUDE.md at your repository root.
Autonomous Editing & Checkpointing Rules
Before modifying or rewriting any existing file:
- ALWAYS archive the exact pre-edit file into
.snapshots/<filepath>/v<OLD_VERSION>.<ext>. - RETENTION LIMIT: Keep at most 5 latest snapshots per file bucket. Prune older versions.
- SEMVER IMPACT: Tag as MAJOR (breaking overhaul), MINOR (additive feature), or PATCH (small fix/refactor).
- TOKEN-OPTIMIZED DUAL-LEDGER:
- Update sharded index at
.snapshots/<filepath>/manifest.json. - Append 1 line to
REVISION_LOG.mdtable:| <Date> | <Version> | <Impact> | <File> | <Snapshot> | <Rationale> | - Never re-read historical
REVISION_LOG.mdentries into context.
- Update sharded index at
- EXCLUSION RULE: Strictly exclude binary weights (.pt, .onnx), datasets > 1 MB, and caches (node_modules, venv, pycache).
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.

