repository-drift-control
Skill12 starsChanged 4 months agoMITView on GitHub
Enforce coordinated updates across specs, templates, prompts, samples, and docs to prevent repository guidance drift.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- create-agents-mdSkill
- create-checkpointSkill
- create-project-instructionsSkill
- create-skillSkill
- create-usercontext-instructionsSkill
- restore-checkpointSkill
- validate-agents-mdSkill
- validate-project-instructionsSkill
- validate-skillSkill
- validate-usercontext-instructionsSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
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 17
Use this skill when specification or governance files change.
- Distinctive: line 18
Use this skill during repo-wide refactors affecting canonical paths or precedence rules.
- Distinctive: line 19
Do not use this skill for isolated content edits without cross-artifact impact.
- Distinctive: line 30
Verify policy and precedence remain coherent after updates.
- Distinctive: line 44
Treat specification as authoritative when conflicts exist.
- Distinctive: line 47
Avoid partial updates that leave dependent artifacts inconsistent.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Repository Drift Control
Purpose
Prevent divergence between authoritative specification, operational prompts/templates, and repository-facing documentation.
When To Use
- Use this skill when specification or governance files change.
- Use this skill during repo-wide refactors affecting canonical paths or precedence rules.
- Do not use this skill for isolated content edits without cross-artifact impact.
Required Inputs
- Changed authoritative artifact(s), especially
specs/context_aware_ai_session_spec.md. - Current canonical path map.
- List of dependent files expected to be audited.
Workflow
- Identify source-of-truth changes and affected dependency set.
- Audit templates, prompts, samples, README, and AGENTS for alignment.
- Apply consistent terminology and path references.
- Verify policy and precedence remain coherent after updates.
- Record drift-control outcomes in commit/PR summary.
Output Expectations
- Aligned artifacts with no stale references.
- Stable canonical paths and precedence documentation.
- Clear audit trail of what was updated and why.
Resources
- Governance contract:
../../AGENTS.md - Repository guide:
../../README.md - Authoritative model:
../../specs/context_aware_ai_session_spec.md
Constraints And Safety
- Treat specification as authoritative when conflicts exist.
- Keep guidance provider-neutral.
- Preserve canonical path stability unless explicitly migrating.
- Avoid partial updates that leave dependent artifacts inconsistent.
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.