epistemic-protocols / katalepsis
AGENTS.md175 starsChanged 37 days agoMITView on GitHub
Responsibility under the Northstar (root AGENTS.md). The protocol here makes sure something in play — code, a document, a result — is actually understood before work builds on it. The AI first shows a map of understanding over the person's purpose and completes it with them, each aspect keeping what the target does there, with its material and results, apart from what the person has said of it — their own reading, or acceptance of the AI's explanation, never taken…
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
- lean/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
katalepsis/ — /grasp
Responsibility under the Northstar (root AGENTS.md). The protocol here makes sure something in play — code, a document, a result — is actually understood before work builds on it. The AI first shows a map of understanding over the person's purpose and completes it with them, each aspect keeping what the target does there, with its material and results, apart from what the person has said of it — their own reading, or acceptance of the AI's explanation, never taken as their understanding — rather than assumed from agreement, until they say what they understand now serves their purpose.
Boundary. skills/grasp/SKILL.md is the contract for /grasp; it names any supporting file in its references/ to read where that file applies. README.md, README_ko.md, and docs/ explain the protocol to people, and .claude-plugin/ and .codex-plugin/ carry what a host needs to list and install it; what the protocol does once invoked is set in the SKILL.md.
Next. skills/grasp/SKILL.md.
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.

