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 skills add mycelium-hq/ai-brain-starter --skill coachgit clone --depth 1 https://github.com/mycelium-hq/ai-brain-starterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/coach)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/coach"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/coach/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/coach"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00103 | $0.03163 |
| Opus 5.5 | $0.00041 | $0.01265 |
| Sonnet 5.5 | $0.00021 | $0.00633 |
| Haiku 4.5 | $0.00010 | $0.00316 |
Grade A, and why
coach 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 1mo 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
coach, the longevity + fitness coach
Reads everything health-mcp knows (recovery, sleep score, sleep regularity, cycle phase, somatic state, longevity panel, out-of-range labs, Floor from today's journal) and issues a prescription that's specific to THIS person on THIS day. Progressive overload tracked per-lift. Deload every 4th week. Calendar drop optional.
This is the substrate's coach SURFACE. The DATA + DECISION layer lives in services/health-mcp/coach.py. The VOICE + WORKOUT TEMPLATES + CALENDAR INTEGRATION live here.
When to use
- User says
/coach,/coach today,/coach week,/coach profile,/coach log - User asks "what should I do today" / "give me a workout" / "build me a week" / "how should I train"
- User wants a longevity plan
- User wants to log a completed workout (RPE + lift actuals)
- User wants to see progression on a specific lift
- Scheduled morning task fires to drop today's workout into calendar
Do NOT use for:
- Importing health data (use
/ingest-healthor/health-setup) - Querying past biometrics without prescribing (use
health_status,health_metric_series) - Building new wearable connectors (substrate dev task)
First time: profile setup
When /coach profile runs (or /coach runs and no profile exists), ask the user these 12 questions and save the answers to <vault>/Meta/coach-profile.yaml. Never re-ask once saved unless they say something changed.
- Primary goal: lose weight, build muscle, run a 5K, get more active, reduce stress, improve mobility, train for a specific event, body recomp, longevity
- Secondary goal: optional
- Equipment: full gym, home dumbbells, barbell + rack, bodyweight only, resistance bands, kettlebells, pull-up bar, cardio machines (multi-select)
- Days/week realistic: 3 / 4 / 5 / 6
- Session length: 20 / 30 / 45 / 60 min
- Time of day: morning / lunch / evening (this affects calendar drop)
- Injuries / limitations / chronic conditions / movements to avoid: free text
- Current fitness level: complete beginner / beginner / intermediate / advanced
- Exercises hated: free text
- Exercises loved: free text
- Floor sensitivity: how much does emotional state shape what training feels right? (low / medium / high) — affects how much weight to give to today's Floor tag
- Longevity priorities: which Attia-style markers matter most? (VO2Max, Zone 2 minutes, lean mass, walking steadiness, sleep regularity, fasting insulin / HbA1c — multi-select)
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.
- 1mo ago First seen · 226 lines · 103 tokens per session scan A cc2e284d3261
coach is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (48 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 3,163 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
nightly
Canonical seven-leg nightly close-parity protocol. Eleven independently evidenced checkpoints cover synthesis, reconciliation, context hygiene, sweeps, heat, digest, runtime health, cognitive state, ledger capture/review, and vault sync.
Promote
Take a slice of the current conversation and promote it to a durable vault artifact — concept note, project update, person profile, or doctrine entry. Pairs with /close. /close writes the daily note (transient outcome record); /promote elevates specific insights to permanent vault content the framework can refer back…
Stuck
Walk the 6-rung escalation ladder before declaring stuck or asking the principal. Most "stuck" is actually "haven't tried the next approach." Stopping is the last resort, not the first response.
open
Boot the session, load context from the vault, and surface what matters.
caddy-mute
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
start
The day-one first-run flow and the everyday home screen. On first launch, greet, run setup, then carry the operator into a real first win. On return, give a short briefing and action menu.