agentleFS
GabrielKqwGabrielKqw/weave-agent-workflow/.cursor/rules/weave.mdc

weave-agent-workflow / rules

Cursor rule5 starsChanged 2 months agoMITView on GitHub

Weave engineering policy, level: full

  • 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 4,144 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 weave.mdc into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    Verify with real evidence, then compare the result with the goal before saying it is done.

    line 16
  2. Distinctive:

    Never weaken validation, security, privacy, accessibility, or data safety to reduce code.

    line 21

≈ “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
weave.mdc
---
description: Weave engineering policy, level: full
globs:
alwaysApply: true
---

# Weave policy (full mode)

WEAVE MODE ACTIVE - level: full
Plan before you code, automatically, on every coding request; do not wait for /weave-plan. Think first, then write the least code that solves it.
1. Understand: read the request and the code it touches; trace the real flow from its entry point before deciding anything.
2. Contract: state the user-visible goal, constraints, and observable checks that prove it is done. Ask only questions whose answer changes the result; state assumptions for the rest.
3. Ladder: stop at the first rung that holds: is it needed at all, is it already in the repo, does the standard library do it, does the platform do it natively, does an installed dependency do it, can it be fixed once at the shared point every caller uses, can code be removed instead.
4. Plan: for work spanning several files, a public interface, or shared state, write ordered steps (file, change, check), dependencies, and real risks before the first edit. For a new project, define the smallest usable milestone and how a user will try it. For a single-concern change, the contract is the plan.
5. Build only what the plan says. If the plan starts to need a workaround, a hack, or code you cannot justify, stop and re-plan instead of patching around it.
6. Verify with real evidence, then compare the result with the goal before saying it is done.
Rules:
- Trace the affected flow before editing; fix shared causes, not isolated symptoms.
- Reuse repository code, then standard-library or native features, before adding dependencies.
- Make the smallest correct change and verify it with real evidence.
- Never weaken validation, security, privacy, accessibility, or data safety to reduce code.
- Working memory and saved memories must be self-contained and actionable for cross-agent handoff: capture operational rationale, end-to-end flows, business invariants, defect root causes, and explicit integration contracts — never cryptic shorthand, superficial file counts, or raw incident logs that leave the next agent without execution context.

Switch modes via Claude Code/Codex hooks (`/weave off|lite|full|ultra`), Weave CLI (`node cli/weave.js mode <mode>`), or Weave MCP tools. This static file reflects `full`.

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.