Multi-agent coordination + persistent memory, semantic negotiation, async rooms, and a shared knowledge graph
Skill Claude CodeCodex
Cheap-model audit of comments and inline docs for temporal/historical narration, overly long prose, over-referencing of GitHub issues / PR numbers / plan-step IDs, and design-justification / conversational residue (comments that defend the approach or echo how the code was steered instead of plainly describing it).…
Skill Claude CodeCodex
Run end-to-end smoke tests for the Mycelium claudecode adapter. Verifies claude CLI prereqs, the SKILL.md + workspace install, and the resident participation loop (mycelium await --loop --exec) where a live claude session picks up an @-mention, reasons, and posts a reply back to the room — including a full…
Skill Claude CodeCodex
Run end-to-end smoke tests for the Mycelium cursor adapter. Verifies cursor-agent prereqs, the resident participation loop (mycelium await --loop --exec) picking up an @-mention and posting a reply, workspace asset drift/healing, auth-failure handling, and an aligner-mediated negotiation with a resident cursor agent.…
Skill Claude CodeCodex
Run end-to-end smoke tests for the Mycelium stack. Verifies install, memory, search, and aligner-mediated coordination to consensus. Use when validating a release, after a deploy, or when something feels broken.
Skill Claude CodeCodex
Regenerate the HTML docs site (CLI Reference, Configuration, content sections) from decorators, the pydantic config schema, and markdown source files.
Skill Claude CodeCodex
Modern Python tooling practices for the mycelium project. Use when installing dependencies, running tools, managing environments, or writing Python code. Always active as a background reference.
Skill Claude CodeCodex
Bootstrap yourself as an ephemeral Mycelium agent when your environment is wired to a hub. Claims a distinct per-session identity (delegated from a shared workload credential, owned by the human), picks up or opens a task on the room's board, and reports progress there. Use at the start of a remote or cloud session…
Skill Claude CodeCodex
A/B test multi-agent consensus quality with and without Mycelium's structured negotiation, using fully-composed agent personas from the agent-personas dataset. Pick a named scenario (e.g. ex07investmentportfolio) and the skill fetches the right personas, builds SOUL.md for each agent, then runs the standard…
Skill Claude CodeCodex
Run precommit checks (lint, format, tests) on the mycelium codebase. Use when the user says /precommit or wants to check code quality before committing.
Skill Claude CodeCodex
Cut a release — commit any staged changes, tag, create GitHub release, and optionally notify Webex. Use when the user says /release, /release --with-webex, or /release --preview.
Skill Claude CodeCodex
Take a screenshot of the running Mycelium app, or of CLI output rendered as a terminal card, or record a short video of a flow with a visible cursor and click/zoom animations. Use when you need to SEE the UI — verifying a frontend change, checking a layout at phone/tablet/desktop widths, driving a multi-step flow and…
Skill Claude CodeCodex
Diagnose and fix common Mycelium installation and runtime issues. Use when encountering errors with mycelium commands, backend connectivity, Docker containers, LLM configuration, memory operations, or database migrations. Triggers on "not working", "error", "failed", "cannot connect", "troubleshoot", "debug", "fix".
Skill Claude CodeCodex
Multi-agent coordination layer with persistent memory. Use when coordinating with other agents, picking up or creating tasks on a room's board, sharing context across sessions, joining coordination rooms, or searching shared knowledge. Triggers on "coordinate", "negotiate", "share memory", "mycelium", "the board"…
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: