install
source · Clone the upstream repo
git clone https://github.com/plurigrid/asi
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/plurigrid/asi "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/teglon-agent-protocol" ~/.claude/skills/plurigrid-asi-teglon-agent-protocol && rm -rf "$T"
manifest:
skills/teglon-agent-protocol/SKILL.mdsource content
Teglon Agent Protocol Skill
Editor-agent protocol in Rust
Source: TeglonLabs/agent-client-protocol
Trit: 0 (ERGODIC) | Substrate: Semantic
α/β/γ
- α: Request/response | β: Schema evolution | γ: Backwards compatibility
GF(3)
narya-proofs (-1) ⊗ teglon-agent-protocol (0) ⊗ free-monad-gen (+1) = 0 ✓
Autopoietic Marginalia
The interaction IS the skill improving itself.
Every use of this skill is an opportunity for worlding:
- MEMORY (-1): Record what was learned
- REMEMBERING (0): Connect patterns to other skills
- WORLDING (+1): Evolve the skill based on use
Add Interaction Exemplars here as the skill is used.