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/rendernpx skills add haabe/mycelium --skill rendergit 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 | $0.00102 | $0.02446 |
| Opus 5 | $0.00051 | $0.01223 |
| Sonnet 5 | $0.00020 | $0.00489 |
| Haiku 4.5 | $0.00010 | $0.00245 |
Grade A, and why
render 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Render Dispatcher
Central entry point + menu for the canvas/state render fleet. Routes intent to specialists or surfaces what's available. Cross-cutting views are research-gated and NOT emitted by default. Completes the v0.40.0-announced render fleet foundation.
When to use
- "Show me the OST" / "render the diamond state" / "visualize the cycles" → dispatcher recommends + routes to the specialist (recommend, do NOT auto-invoke).
- "Visualize how opportunity X became cycle Y" → cross-cutting traceability intent. Dispatcher surfaces that the view is research-gated; does not emit a default rendering.
- Discovery: "what renderable views does Mycelium have?" → dispatcher lists specialists + their states.
When NOT to use
- If the user names a specialist directly (
/mycelium:diamond-render,/mycelium:ost-render,/mycelium:cycle-render), the specialist is the one-hop path. Do NOT re-route through the dispatcher. - For cross-cutting views that already have dedicated skills (e.g.,
/mycelium:framework-healthis its own audit; not a render specialist).
Identifier exposure
Declared: MIXED
Scope (per-canvas table — REQUIRED for MIXED)
| Canvas | Exposure | Identifier-bearing fields | Activated when |
|---|---|---|---|
.claude/canvas/opportunities.yml |
YES | evidence_sources, notes |
--view traceability (deferred), --view ost-summary |
.claude/canvas/cycle-history.yml |
YES | learnings.process prose, related_corrections |
--view traceability (deferred), --view cycle-summary |
.claude/canvas/archived-solutions.yml |
YES | discard_notes prose |
--view traceability (deferred), --view discards |
.claude/canvas/landscape.yml |
YES (low) | notes, evidence_sources |
--view competitive-landscape (deferred) |
.claude/diamonds/active.yml |
NONE | none | any view including the diamond |
Rationale
Dispatcher behavior depends on which cross-cutting view is invoked. MIXED with per-canvas scoping is the only honest declaration: YES would force registry consultation on diamond-only views (unnecessary cost); NONE would silently leak identifiers on traceability views (incident). Each cross-cutting view's implementation MUST consult the registry per engine/render-conventions.md#hard-rule-consent--privacy-gate for the YES-exposure canvases it activates and skip the consultation only for NONE-exposure canvases.
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 · 165 lines · 102 tokens per session scan A b2840cca9a25
render is a skill published in the GitHub repository haabe/mycelium (45 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 2,446 once invoked, about $0.0005 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.
prd-v05-technical-stack-selection
Determine technologies needed to build the product, making build/buy/integrate decisions during PRD v0.5 Red Team Review. Handles both greenfield and brownfield contexts. Triggers on requests to select tech stack, evaluate technologies, make build vs. buy decisions, discover existing assets, or when user asks "what…
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-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…
prd-v07-test-planning
Define test cases BEFORE implementation, ensuring every API, business rule, and user journey has verifiable acceptance criteria during PRD v0.7 Build Execution. Triggers on requests to define tests, plan test coverage, create test cases, or when user asks "define tests", "test planning", "what to test?", "test cases"…
prd-v08-monitoring-setup
Define monitoring strategy, metrics collection, and alerting thresholds during PRD v0.8 Deployment & Ops. Triggers on requests to set up monitoring, define alerts, or when user asks "what should we monitor?", "alerting strategy", "observability", "metrics", "SLOs", "dashboards", "monitoring setup". Outputs MON…