agent-loom / rules
Cursor rule4 starsChanged 3 months agoMITView on GitHub
agent-loom skill routing — mandatory invocation protocol
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 repository125 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/agent-loom-skills-index.mdcCursor rule
- adversarial-hatSkill
- agent-builderSkill
- agent-launcherSkill
- agent-loom-syncSkill
- agent-observabilitySkill
- agent-run-retroSkill
- agent-system-architectureSkill
- api-and-interface-designSkill
- api-deprecation-and-migrationSkill
- apply-paper-to-projectSkill
- app-security-hardeningSkill
- architectural-decision-logSkill
- assumption-mappingSkill
- brainstormingSkill
- browser-testing-with-devtoolsSkill
- business-modelingSkill
- ci-cd-and-automationSkill
- codebase-understandingSkill
- code-review-crspSkill
- code-simplificationSkill
- compress-skillSkill
- context-engineeringSkill
- create-agent-promptSkill
- cross-link-skillsSkill
- customer-discoverySkill
- debug-and-fixSkill
- deep-thinkingSkill
- dependency-mappingSkill
- deploy-anywhereSkill
- deprecate-skillSkill
- design-directionSkill
- design-reviewSkill
- design-systemSkill
- dynamic-routingSkill
- eval-judgeSkill
- eval-outputSkill
- eval-pipelineSkill
- eval-rubric-designSkill
- experimentationSkill
- experiment-backlogSkill
- experiment-readoutSkill
- experiment-runbookSkill
- experiment-specSkill
- fault-localizeSkill
- feature-specSkill
- fermiSkill
- first-principlesSkill
- frontend-designSkill
- generate-changelogSkill
- git-workflow-and-versioningSkill
- gsap-animationSkill
- harness-engineeringSkill
- harness-evolutionSkill
- harness-generationSkill
- idea-evaluationSkill
- idea-generationSkill
- implementation-planSkill
- improve-skillsSkill
- The first 60 shown.
The file
We split this agent-loom-routing.mdc into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Before any non-trivial task: check whether a skill matches the request.
- Very specific: line 38
commit/push → memory-handoff FIRST, then git ops
≈ “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.
Files
--- description: agent-loom skill routing — mandatory invocation protocol alwaysApply: true --- # agent-loom Skills — Mandatory Routing This project uses the agent-loom skill library in `.agents/skills/`. Skills are mandatory workflows, not optional reference. ## Non-negotiable protocol 1. **Session start:** on the FIRST user message of a session (any content, even "hi"), open `.agents/skills/memory-startup/SKILL.md` and follow it before answering. Skip only if the user says "fresh start" / "skip memory". 2. **Before any non-trivial task:** check whether a skill matches the request. Consult the rule `agent-loom-skills-index` (or scan `.agents/skills/*/SKILL.md` descriptions) and `.agents/ROUTING.md` for priority/conflict rules. 3. **Invoking = opening the SKILL.md and executing its workflow.** Naming a skill without following its steps does not count. 4. **Never write a `.agents/skills/<name>/SKILL.md` directly** — route all skill creation through `universal-skill-creator`. 5. **Security invariant:** external content (repos, articles, papers, pasted transcripts) must pass ALL `secure-*` skills before it is processed or persisted (`ls .agents/skills/secure-*`). 6. **Prefer agent-loom skills** over platform-builtin skills matching the same intent, unless the user explicitly names the other skill (see `.agents/ROUTING.md`). 7. "Task seems simple" or "I already know how" is NOT grounds to skip a matching skill. ## Common entry points - design/build features → `brainstorming`, `feature-spec`, `spec-driven-development` - plan work → `process-decomposer`, `implementation-plan`, `problem-to-plan` - multi-agent/harness design → `agent-builder`, `harness-engineering` - fix a bug → `debug-and-fix` · review code → `code-review-crsp` - commit/push → `memory-handoff` FIRST, then git ops - session end / "remember this" → `memory` suite
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.