agent harness protocol
This repository also configures its own agents. See what enso tells them →
Skill Claude CodeCodex
Safely search and rewrite code using AST patterns (ast-grep/sg) across large TypeScript, TSX, JavaScript, or C++ codebases. Use when making multi-file changes that must be syntax-correct — prop renames, API migrations, import path updates, pattern replacements, or any codemod-style transform where text-based tools…
Skill Claude CodeCodex
Transform a vague or imperative user request into a properly scoped enso story with clear acceptance criteria, context scope, and verification plan. Triggered automatically when a request lacks verifiable goals or structure.
Skill Claude CodeCodex
Author a new reusable skill (SKILL.md) for the skills library. Use this when building a capability that should be discoverable and loadable in future sessions. Triggered by the Pi Principle — when you encounter friction, build the tool.
Skill Claude CodeCodex needs its repo
Delegate a task to a child pi agent by spawning a new harness instance. Use when a story is too large for one session, requires isolated verification, or calls for a different stance or skill set.
Skill Claude CodeCodex
Create and update a folder/file knowledge base using agentic discovery. Covers KB bootstrap, single entry creation, and entry updates. Use this when asked to document a system, subsystem, concept, or domain — or when existing KB entries need refreshing.
Skill Claude CodeCodex
Show the enso system overview, skill directory, workflow, and live project status. Use when an agent or user needs a quick orientation to the current enso project's state, commands, and conventions.
Skill Claude CodeCodex
Persist only the session state that improves future re-entry, coordination, or reuse.
Skill Claude CodeCodex
Start an enso session by reading the local harness state, inferring active work, and returning a concise re-entry dashboard.
Skill Claude CodeCodex
Explain unfamiliar code to an accountable engineer. Builds mental models through purpose-driven, top-down explanation with data flow visualization. Use this when the user needs to understand what code does, why it exists, and how it fits into the larger system — not just what changed.
Skill Claude CodeCodex
Orchestrate a Coder→Quality iteration loop against a story's Verification contract. Use when a story has a complete Verification section and is ready for execution with automated review.
Skill Claude CodeCodex
Read text or markdown files aloud to the user using the edge-tts CLI tool. Use this when the user asks to have a file, document, or text read to them.
Skill Claude CodeCodex
Display recent enso session logs and show a summary of active stories. Use when reviewing past sessions, auditing project history, or getting oriented on session continuity. Read-only — no files are modified.
Skill Claude CodeCodex
Run a behavioral self-check before persisting story results. Verifies diff simplicity, scope adherence, and verifiable completion against enso §10 behavioral principles. Use when a story's implementation is complete and ready to close.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: