epistemic-protocols / lean
AGENTS.md175 starsChanged 37 days agoMITView on GitHub
Responsibility under the Northstar (root AGENTS.md). The Northstar calls the protocols a metalanguage of structured types; this directory is where those types are made precise enough for a machine to check. A protocol's SKILL.md carries a Lean block that models its contract, and what is stated and proved about that model lives here. Boundary. EpistemicProtocols/Ground.lean and EpistemicProtocols/ToolGrounding.lean are the shared sections every protocol block carries verbatim. EpistemicProtocols/<Protocol>/Theorems.lean states and proves the guarantees of one protocol's block. Audit/ checks the blocks…
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- aitesis/AGENTS.mdAGENTS.md
- analogia/AGENTS.mdAGENTS.md
- anamnesis/AGENTS.mdAGENTS.md
- .claude/principles/AGENTS.mdAGENTS.md
- design/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- epharmoge/AGENTS.mdAGENTS.md
- epistemic-cooperative/AGENTS.mdAGENTS.md
- euporia/AGENTS.mdAGENTS.md
- heuresis/AGENTS.mdAGENTS.md
- horismos/AGENTS.mdAGENTS.md
- hyphegesis/AGENTS.mdAGENTS.md
- hypotyposis/AGENTS.mdAGENTS.md
- katalepsis/AGENTS.mdAGENTS.md
- merismos/AGENTS.mdAGENTS.md
- periagoge/AGENTS.mdAGENTS.md
- proplasma/AGENTS.mdAGENTS.md
- route/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- encapsulationSkill
- formal-reviewSkill
- outcomeSkill
- realizeSkill
- rederiveSkill
- releaseSkill
- verifySkill
The file
Files
lean/
Responsibility under the Northstar (root AGENTS.md). The Northstar calls the protocols a metalanguage of structured types; this directory is where those types are made precise enough for a machine to check. A protocol's SKILL.md carries a Lean block that models its contract, and what is stated and proved about that model lives here.
Boundary. EpistemicProtocols/Ground.lean and EpistemicProtocols/ToolGrounding.lean are the shared sections every protocol block carries verbatim. EpistemicProtocols/<Protocol>/Theorems.lean states and proves the guarantees of one protocol's block. Audit/ checks the blocks against the definition rules, and Tests/ holds fixtures that break those rules on purpose. The contract text itself stays in the protocol's SKILL.md; the modules built from it are generated, not checked in. A property proved here holds under the judgments the block leaves open, which it takes as assumptions.
Next. lakefile.toml at the repository root for how the pieces build, then the Theorems.lean of the protocol in question.
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.

