agentleFS
Sign inStart free
igorkravcenkoigorkravcenko/snowshoe/.cursor/rules/project.mdc

snowshoe / rules

Cursor rule1 starsChanged 35 days agoApache-2.0View on GitHub

Snowshoe product identity and spec-driven brain OS

  • 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 4,181 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 repository9 other files it gives its agents.

The file

We split this project.mdc into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not v1: chat hell, AI code review, multiplayer knowledge graph, agent HITL/control plane.

    line 15
  2. Very specific:

    Do not invent ARR, users, or competitors.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
project.mdc
---
description: Snowshoe product identity and spec-driven brain OS
alwaysApply: true
---

# Snowshoe

Working name (provisional): **Snowshoe**.
Subtitle: **Don't let your agents outrun your understanding. Keep your footing.**

Git-native personal comprehension map of a repository (ledger is personal/local). Freshness after commits or pull; the human chooses what to catch up on.

v1 surfaces (intent): signal after pull + PR-check. Default signal is skill/human → CLI (`snowshoe …`; informal *snow* is not CLI). `init` does not install git hooks; opt-in hooks remain intent (CLI not shipped).

Not v1: chat hell, AI code review, multiplayer knowledge graph, agent HITL/control plane.

**Implementation status:** HP1–4 CLI + tryable map UI/skill (no learning). Do not add learning/quiz/verify, hook install, agent spawn, or fake features unless `docs/brain/CURRENT.md` and an ADR say so. CI: `brain-docs` lint plus app CI (typecheck / `bun test` / Biome) per `ADR-2026-09-25-brain-docs-ci` and `ADR-2026-09-27-app-ci-biome`. No lefthook/husky yet.

## Brain OS

- Entrypoint: `AGENTS.md` → `docs/brain/START_HERE.md`
- Truth: `docs/brain/CURRENT.md` + accepted ADRs under `docs/brain/DECISIONS/`
- `EXPERIMENTS.md` is a registry, not truth
- `docs/evidence/**` is support, not truth
- Research docs carry YAML `status:` frontmatter
- Behavior or product-claim changes require an ADR **and** a CURRENT update in the same change
- Protocol: `.cursor/skills/brain-protocol/SKILL.md`
- Maintainer overlay (optional): `./scripts/link-private-overlay.sh` from sibling `snowshoe-maintainers` → `.cursor/skills/gan-*` + `docs/private` + optional `maintainer-chat.mdc`. GAN fail-closed if not in Orca. Public canon must not link `docs/private`. Product does not depend on the overlay.
- Docs PR quality: CoS merge QC uses `.cursor/skills/consistency-audit` before merge; CI is a tripwire only. Brain staleness stays `grill-canon`.

Do not invent ARR, users, or competitors. Unknown stays `unknown`.

This repo is not a trading stack. Do not copy Nautilus, portfolio, bots, or related domain from other projects.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free