Plugin Claude Code
Discovery before delivery, enforced by hooks rather than prose. Single-plugin marketplace.
Plugin Claude Code
Discovery before delivery, enforced by hooks rather than prose. Single-plugin marketplace.
Settings file Claude Code
Agent settings declaring 23 allowed tools.
Instructions file CodexOpenCode
Instructions for haabe/mycelium, covering agents, if you are operating in this repo, what's available, minimal path (any agent) and concrete operating model per agent class.
Instructions file
Instructions for haabe/mycelium, covering mycelium: theory-guided agentic product development, agent operating contract (always-on rules), the diamond engine, diamond scales (l0-l5) and diamond phases.
Plugin Claude Code
I realized I let the agent start coding before I was sure it was working on the right thing, so I built this. Now it doesn't get to write code before there's a reason. The agent asks who this is for. It asks what you're assuming, and what would show you wrong. The rules run as hooks, so the build stays shut until the…
Hook
Runs before the agent uses a tool for Write, Edit, MultiEdit, Bash, mcp__filesystem__(write_file, edit_file, move_file), WebSearch, WebFetch, mcp__brave-search__.* and mcp__fetch__fetch tool calls, executing gate.sh, discovery-gate.sh, brownfield-gate.sh, scope-gate.sh, framework-guard.sh…
Hook
Runs after a tool call finishes for Write, Edit, MultiEdit and Read tool calls, executing post-write-nudge.sh, change-log.sh, diamond-state-audit.sh and read-log.sh via bash (4 commands). From haabe/mycelium.
Hook
Runs when a tool call fails for Bash tool calls, executing reflexion-gate.sh via bash. From haabe/mycelium.
Hook
Runs when the agent finishes a response, executing stop-check.sh and ci-signal.sh via bash (2 commands). From haabe/mycelium.
Hook
Runs when a session starts on startup, resume, clear and fork, executing session-start.sh and ci-signal.sh via bash with --session-start (2 commands). From haabe/mycelium.
Hook
Runs when you submit a prompt, before the agent sees it, executing preflight.sh and discovery-trigger-guard.sh via bash (2 commands). From haabe/mycelium.
Skill Claude CodeCodex
Accessibility audit against WCAG 2.1 AA. Checks semantic HTML, ARIA, keyboard navigation, color contrast, screen reader compatibility.
Skill Claude CodeCodex
Bring Mycelium into a project that already has code. Detects that the repo predates the framework, asks before touching anything, then reads the codebase to draft what it CAN establish (delivery, solution shape) and — the actual point — names what it cannot (purpose, strategy, real user evidence). The output is a…
Skill Claude CodeCodex
Design the smallest viable test to validate or invalidate a critical assumption. Based on Torres's assumption testing framework, organized by Gilad's AFTER model (Assessment → Fact-Finding → Tests → Experiments → Release Results).
Skill Claude CodeCodex
Use before any research activity or significant decision. Reviews cognitive biases relevant to the current stage.
Skill Claude CodeCodex
Use to evaluate whether current work aligns with Better Value Sooner Safer Happier. Run at diamond completion and periodically.
Skill Claude CodeCodex
Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions.
Skill Claude CodeCodex
Synchronize canvas state across team sessions via git. Ensures all team members see the same product knowledge.
Skill Claude CodeCodex
Update canvas sections with new evidence. Ensures canvas stays current as the single source of truth.
Skill Claude CodeCodex
Use to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns.
Skill Claude CodeCodex
Render .claude/canvas/cycle-history.yml as a Gantt chart + outcome distribution pie (or ascii / json). Read-only. Consults the attribution registry per ${CLAUDEPLUGINROOT}/engine/render-conventions.md consent + privacy gate. Third specialist in the render fleet.
Skill Claude CodeCodex
Use when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropriate methods.
Skill Claude CodeCodex
Pin a measurable, outcome-based Definition of Done for a diamond — a behaviour-change that creates value, not a build-list. Problem-first Socratic sequence; writes definitionofdone to the diamond at birth or retrofits it when missing.
Skill Claude CodeCodex
Use to verify a feature/story meets all Definition of Done criteria before marking complete.