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-pre-workout-briefgit 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-pre-workout-brief)<a href="https://agentmods.dev/skills/philipyaz/cos/fitness-pre-workout-brief"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-pre-workout-brief/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-pre-workout-brief"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-pre-workout-brief.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 | $0.00242 | $0.04944 |
| Opus 5 | $0.00121 | $0.02472 |
| Sonnet 5 | $0.00048 | $0.00989 |
| Haiku 4.5 | $0.00024 | $0.00494 |
Grade B, and why
fitness-pre-workout-brief scanned grade B with 2 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 11d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
to you. Never tell the user to "click Generate" — **you** author the brief and `save_*` it. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`bash`/`curl` (Cowork's sandbox blocks outbound HTTP; the tools exist for exactly this). How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-workout brief (today's go / hold-back call)
This skill is the intelligence that turns "should I train today?" into a persisted
pre-workout brief on the board. It runs only through the fitness MCP — never
bash/curl (Cowork's sandbox blocks outbound HTTP; the tools exist for exactly this).
/fitness/pre-workout-brief is the read twin: a history feed (latest-by-default,
page-back) over the saved briefs; the human glances at it, you author and persist the
brief.
The board is a state machine; YOU are the intelligence. There is no board-side LLM —
the page's Generate action hands off to you, not to a server-side coach. The one number
you do not invent is the form score: the board computes it deterministically
(get_form_score) and you read + interpret it — you never recompute it. Everything else
(the readiness call, the session adjustment, the warnings, the green lights, the one-liner)
is your judgement, then you save_pre_workout_brief it.
Scope. This skill is the daily brief only. The weekly training plan (
fitness-training-plan), the weekly review (fitness-weekly-review), the profile (fitness-athlete-profile), and correlations (fitness-correlations) are their own focused skills — defer there for "make me a plan for the week", "how was my training this week", "set my profile". Here you read today's recovery + the day's planned session and give the go / easier / rest call.
Gate — the add-on must be ENABLED. The WRITE (
save_pre_workout_brief) 404s ("Not found — the fitness add-on may be disabled.") when the Fitness add-on is disabled; the READS (get_form_score,get_daily_summary,list_health_data,get_athlete_profile,list_coaching_artifacts) always work. If the save comes back 404, the add-on is off — tell the user to enable it from the board's /addons catalog (toggle on), then retry. You don't enable the add-on yourself.
NOT MEDICAL ADVICE — say it. A brief is an informational estimate, not medical advice. A "go easy / rest" read on low HRV or poor sleep is a conservative training default, not clinical judgement. Defer to a professional (physician, physiotherapist, qualified coach) for any injury, pain, illness, chest pain or abnormal symptom, pregnancy, or a user under 18 — recommend they consult one and don't push hard training. Carry that framing in your own words.
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.
- 11d ago First seen · 293 lines · 242 tokens per session scan B 7e09f71268aa
fitness-pre-workout-brief is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed yesterday), licensed MIT. It adds 242 tokens to every session and 4,944 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 2 findings (subtle steering, makes network calls). 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…