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 philipyaz/cos --skill fitness-training-plangit clone --depth 1 https://github.com/philipyaz/cosWrote 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/philipyaz/cos/fitness-training-plan)<a href="https://agentmods.dev/skills/philipyaz/cos/fitness-training-plan"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-training-plan/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/philipyaz/cos/fitness-training-plan"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-training-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00227 | $0.05817 |
| Opus 5 | $0.00113 | $0.02908 |
| Sonnet 5 | $0.00045 | $0.01163 |
| Haiku 4.5 | $0.00023 | $0.00582 |
Grade A, and why
fitness-training-plan 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 6d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fitness — weekly training plan (the headline coaching skill)
This is the flagship of the Fitness coach: it turns "plan my week" / "I'm
training for an Olympic tri in September, build this week" into a 7-day,
day-by-day training plan that is personalised to the athlete's goal +
constraints, adapted to their current recovery, and — the whole point —
deliberately VARIED against the recent plans/workouts so the athlete isn't fed
the same week on repeat. You author the plan in your own reasoning, then
persist it via the fitness MCP's save_training_plan so it lands on the
/fitness/training-plan history feed.
The board is a state machine; YOU are the coach. There is no board-side LLM
— the board never designs a plan. The /fitness/training-plan page is a history
feed over persisted training_plan artifacts (latest-by-default, page-back); its
Generate action hands off to you, it does not call a server-side model. So
never tell the user to "click Generate and wait" — you generate, you
save_training_plan, and the result appears on the feed.
Gate (same as fitness-coach).
save_training_planis an add-on-gated write — it 404s ("Not found — the fitness add-on may be disabled.") when the Fitness add-on is off (tell the user to flip it on at /addons; you don't enable it yourself). All the READ tools below are ungated — read freely.
STEP 0 — the mode switch. Read
config/auto-sync.json→{ "autoSync": <bool> }(default ON / auto if missing) and state the mode once. Saving one plan is a single low-stakes write — just do it in either mode. The conversational confirm is reserved for the bulk calendar push (STEP 8) and any destructive action.
NOT MEDICAL ADVICE. A training plan is an informational estimate, not medical advice. A "train easy / take a recovery day" call on low HRV or poor sleep is a conservative default, not clinical judgement. Defer to a professional (physician, physiotherapist, qualified coach) for any injury, pain, abnormal symptom, medical condition, pregnancy, or an under-18 athlete — recommend they consult one and don't prescribe hard training.
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.
- 6d ago Changed · +28 lines 2a4f8e4093c7
- 11d ago First seen · 319 lines · 227 tokens per session scan A f965890fe082
fitness-training-plan is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 227 tokens to every session and 5,817 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
write-bundle
Run several vault writes as ONE logical operation with rollback — the note + the index + the journal + hot.md either all land, or none do. Use whenever a single user-visible action touches 2+ files and a half-written result would be wrong. Also the recovery entry point for bundles a crash left unfinished. EN triggers…
canvas
Create or modify Obsidian canvas (.canvas) files — visual layout layer where wiki pages, images, PDFs, and free-form text cards are arranged spatially. Supports adding nodes, defining zones (labeled regions), and laying out content with auto-positioning. Use when the user says "create a canvas", "add to canvas"…
write-frontmatter-merge
Apply multiple frontmatter updates at once (sequential, NOT atomic — partial failures are reported per-key). Use when you want to update 2+ properties on the same file in one call. EN triggers: "update multiple properties on X", "set status, score, and tags on X", "mark Y as closed with outcome stopped", "bulk-update…
template-execute
Execute a Templater template, optionally writing the rendered output to a new file. Arguments are exposed to the template via tp.mcpTools.prompt("key") (directly under tp, NOT under tp.user — easy footgun). EN triggers: "render the X template", "run the daily template", "execute Templates/X.md with arg1=v1", "use…
read-search
Plain-text (substring) search inside a vault, with surrounding context. EN triggers: "find in my vault", "search for the literal string X", "grep for X", "where do I mention X", "find files containing X". FR triggers : "trouve dans mon vault", "cherche la chaîne X littéralement", "grep ", "où est-ce que je mentionne…