consolidation-memory
Copilot instructions8 starsChanged 9 months agoMITView on GitHub
Read before suggesting or applying changes: Claims are reusable beliefs; episodes are evidence. This is a trust layer, not generic RAG. M1 — LLM-optional substrate. See unchecked items in docs/AGENT_GOAL.md.
Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,397 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/consolidation-memory.mdcCursor rule
- releaseSkill
- reviewSkill
The file
We split this copilot-instructions.md into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 3
Read before suggesting or applying changes:
- Very specific: line 15
Prefer deterministic logic in consolidation/fast_path.py over LLM prompt changes.
- Very specific: line 16
Keep Python / MCP / REST / OpenAI tool semantics aligned via query_service.py.
- Very specific: line 17
Add tests for behavior changes.
- Very specific: line 18
Use additive DB migrations in database.py when schema changes.
≈ “Common” is an estimate: at least 1 in 5 of the 3,854 Copilot instructions 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
Copilot instructions — consolidation-memory
Read before suggesting or applying changes:
docs/AGENT_GOAL.md— current milestone and next taskdocs/VIBECODING.md— trust invariants, verification, milestone orderAGENTS.md— session workflow
Product stance
Claims are reusable beliefs; episodes are evidence. This is a trust layer, not generic RAG.
Coding rules
- Prefer deterministic logic in
consolidation/fast_path.pyover LLM prompt changes. - Keep Python / MCP / REST / OpenAI tool semantics aligned via
query_service.py. - Add tests for behavior changes; run
ruff check src testson touched files. - Use additive DB migrations in
database.pywhen schema changes.
Current focus
M1 — LLM-optional substrate. See unchecked items in docs/AGENT_GOAL.md.
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.

