steepy-formula
AGENTS.md5 starsChanged 19 days agoApache-2.0View on GitHub
Land governed project knowledge in a canonical Stable Knowledge Graph, route work by surface, and keep it coherent with graph validation. For every task, use the steepy-formula-bootstrap skill first. If that skill is unavailable, run steepy-formula hub-mode and quote the mode: line. If it reports migrate, stop and tell the user to run the graph-migrate skill; if it reports none, stop and tell the user to run the init skill. Otherwise, resolve the task context with steepy-formula context resolve --path…
In this repository15 other files it gives its agents.
- templates/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- steepy-formula-bootstrapSkill
- steepy-formula-bootstrapSkill
- brainstormSkill
- checkSkill
- discoverySkill
- graph-migrateSkill
- implementSkill
- inceptionSkill
- initSkill
- loop-engineerSkill
- new-surfaceSkill
- planSkill
- reviewSkill
The file
Files
<!-- steepy:managed:project-instructions:v1:start -->steepy-formula
Land governed project knowledge in a canonical Stable Knowledge Graph, route work by surface, and keep it coherent with graph validation.
Development commands
npm testnode --test tests/adapters.test.mjsnode --test tests/workflow-skills.test.mjsnode --test tests/template.test.mjs tests/project-scaffold.test.mjs
Confirmed surfaces
adapters(adapters) —adapters-agentscripts(scripts) —scripts-agentskills(skills) —skills-agenttemplates(templates) —templates-agenttests(tests) —tests-agent
Project navigation
For every task, use the steepy-formula-bootstrap skill first. If that skill is unavailable, run steepy-formula hub-mode and quote the mode: line. If it reports migrate, stop and tell the user to run the graph-migrate skill; if it reports none, stop and tell the user to run the init skill. Otherwise, resolve the task context with steepy-formula context resolve --path <task-path> (fallback --target apex:<projectId>:surface:<slug>) and load exactly what it returns.
<!-- steepy:managed:project-instructions:v1:end -->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.