consolidation-memory / rules
Cursor rule8 starsChanged 9 months agoMITView on GitHub
Consolidation-memory development rules — trust invariants and verification
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,329 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
- .github/copilot-instructions.mdCopilot instructions
- releaseSkill
- reviewSkill
The file
We split this consolidation-memory.mdc into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- could be automatic: a setting could enforce it
- Distinctive: line 21
If memory tools are unavailable, say so once and continue without fabricating results.
- Distinctive: line 25
Read CONTRIBUTING.md — trust invariants and verification commands.
- Distinctive: line 26
Read docs/ARCHITECTURE.md when touching persistence, recall, or consolidation.
- Very specific: line 31
Prefer deterministic consolidation (consolidation/fast_path.py) over new LLM prompts for core behavior.
- Very specific: line 32
Add tests; run targeted pytest + ruff check src tests before claiming done.
- Very specific: line 38
Add MCP/REST features without schemas.py parity.
≈ “Common” is an estimate: at least 1 in 5 of the 6,873 Cursor rule 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
--- description: Consolidation-memory development rules — trust invariants and verification alwaysApply: true --- # consolidation-memory agent rules You are working on **consolidation-memory**: a local-first, trust-calibrated belief layer for coding agents. ## Memory first (mandatory) `consolidation_memory` MCP is configured. On **every user turn**, call `memory_recall` as your **first** tool — before shell, reads, edits, searches, or subagents. 1. `memory_recall` with a query from the user's goal (`include_knowledge=true`). 2. `python scripts/sync_working_copy.py` when the git tree is clean (keeps `main` on `origin/main`). 3. Then proceed with other work. 3. `memory_store` after meaningful progress; `memory_detect_drift` after substantial edits. 4. Final `memory_recall` before closing the turn. If memory tools are unavailable, say so once and continue without fabricating results. ## Before coding 1. Read [CONTRIBUTING.md](CONTRIBUTING.md) — trust invariants and verification commands. 2. Read [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) when touching persistence, recall, or consolidation. ## Non-negotiable - Preserve temporal correctness, provenance, contradiction visibility, drift auditability, scope isolation, surface parity. - Prefer deterministic consolidation (`consolidation/fast_path.py`) over new LLM prompts for core behavior. - Add tests; run targeted `pytest` + `ruff check src tests` before claiming done. - Ship schema changes only with `CURRENT_SCHEMA_VERSION` migrations and `ensure_schema()` tests. ## Do not - Rewrite `client.py` or `consolidation/engine.py` in one pass. - Add MCP/REST features without `schemas.py` parity. - Skip tests for trust-impacting behavior changes.
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.

