Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/haabe/mycelium/startnpx skills add haabe/mycelium --skill startgit clone --depth 1 https://github.com/haabe/myceliumWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00070 | $0.02404 |
| Opus 5 | $0.00035 | $0.01202 |
| Sonnet 5 | $0.00014 | $0.00481 |
| Haiku 4.5 | $0.00007 | $0.00240 |
Grade A, and why
start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mycelium:start — combined first-time entry
When this skill runs, follow the flow below. The skill is designed so a first-time user goes from "plugin installed" to "holding a one-page brief on their idea" in a single invocation.
Step 1: Welcome (~30 seconds of context, then move on)
Output a short welcome before doing anything. Do NOT skip this — the install-to-here gap is the friction point this skill exists to address. The user just installed a 45-skill framework and has no context yet.
"Welcome to Mycelium.
Mycelium makes the agent think before it builds — it can't skip the hard questions; each step has to clear an evidence check first. Grounded in 30+ established product-thinking frameworks; you'll meet the relevant ones as they come up.
Two quick steps:
- Set up Mycelium's files in
.claude/— about 10 seconds. Your existing files (CLAUDE.md, README, etc.) aren't touched; only a new.claude/directory is added.- A 10-minute discovery brief: 4 questions about your idea, then a one-page brief covering who it's for, the biggest assumption, the biggest risk, and your next concrete move.
Let's begin."
Step 2: Detect existing state — HARD GATE
This must be the very first action after the welcome. Do NOT run any other Bash commands, Edit/Write operations, or "let me prepare the directories" reasoning before this gate fires.
Run exactly this check, and only this check:
test -f "$CLAUDE_PROJECT_DIR/.claude/diamonds/active.yml"
- If exit code 0 (file EXISTS): the project already has Mycelium state. Skip directly to Step 4 routing output. Do NOT run setup. Do NOT run mkdir. Do NOT touch
.gitkeepstubs. Setup-style operations on an already-initialized project waste tokens and trigger Read-before-Write tool errors when the agent then tries to write to existing files. Detected during 2026-05-09 plugin-form dogfood — the agent ranmkdir -p .claude/...before honoring this gate, then hit a Write error onactive.ymland only then realized the project was initialized. The fix is structural: the gate is the first action.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 132 lines · 70 tokens per session scan A ae956eed74f9
start is a skill published in the GitHub repository haabe/mycelium (45 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 2,404 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
context-manager
Context management skill providing discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows for project context.
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.
prd-v07-implementation-loop
Execute implementation within EPICs following test-first development, continuous SoT updates, and code traceability during PRD v0.7 Build Execution. Triggers on requests to start building, implement an epic, begin coding, or when user asks "start building", "implement epic", "coding", "development", "build execution"…
prd-v06-architecture-design
Define how system components connect, establishing boundaries, patterns, and integration approaches during PRD v0.6 Architecture. Triggers on requests to design architecture, create system design, define component relationships, or when user asks "design architecture", "system design", "how do components connect?"…
prd-v07-epic-scoping
Transform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution. Triggers on requests to create epics, scope work, break down implementation, or when user asks "create epics", "scope work", "break down work", "context window sizing", "what to build first?", "implementation…
prd-v08-runbook-creation
Create operational playbooks for incident response, deployments, and maintenance during PRD v0.8 Deployment & Ops. Triggers on requests to create runbooks, document procedures, or when user asks "how do we handle incidents?", "runbook", "operational procedures", "on-call guide", "incident response", "maintenance…