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 instructions/almostjacked/fitness-tools/agents-mdgit clone --depth 1 https://github.com/almostjacked/fitness-toolsWrote 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/instructions/almostjacked/fitness-tools/agents-md)<a href="https://agentmods.dev/instructions/almostjacked/fitness-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/almostjacked/fitness-tools/agents-md.svg" alt="Measured on agentmods" 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 | $0.00930 | $0.00930 |
| Opus 5 | $0.00465 | $0.00465 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
fitness-tools AGENTS.md 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and humans) working on this repository. If you are an agent using the calculators (calling the MCP/HTTP tools), see the consumer guide instead.
What this repo is
A pnpm monorepo of deterministic fitness calculators. Three independently published artifacts share one core:
packages/core—@almostjacked/fitness-tools, the library. This is the product.apps/api—@almostjacked/fitness-tools-api, a reference HTTP server over the core.apps/mcp—@almostjacked/fitness-tools-mcp, an MCP stdio server over the core.apps/docs— the Astro/Starlight documentation site.
The API and MCP are thin protocol shells: identical math, different transport.
Setup
corepack enable # pnpm version is pinned in package.json
pnpm install
pnpm -C packages/core build # api/mcp import the core's built dist/
Everyday commands
pnpm -r test # all suites (core + api + mcp)
pnpm -r typecheck # tsc --noEmit across packages
pnpm -C packages/core test:watch # watch the calculators while editing
pnpm -C packages/core build # emit dist/ + .d.ts
pnpm -C apps/api dev # reference HTTP server on :8080
pnpm -C apps/mcp dev # MCP stdio server (tsx watch)
pnpm -C apps/docs dev # docs site
Golden rules (do not violate)
- Test-driven. Write a failing test first, then the minimal code to pass it.
- Calculators are pinned to published reference values. Each formula is tested against a known number from its source. Never edit a pinned expected value just to make a test pass. If it's off, fix the formula, or adjust the tolerance to the source's stated accuracy and explain why in the PR.
- Outputs are the public contract. Changing what a calculator returns — even a rounding tweak that looks like a "fix" — is a breaking change (major version). Downstream users depend on the exact numbers.
- Never hand-edit the README tools table between the
<!-- tools:start/end -->markers. Regenerate it:pnpm -C packages/core gen:tools(a test fails if it drifts). - Every registered tool needs a per-tool docs page under
apps/docs/src/content/docs/tools/. A test fails if one is missing. - Keep
maingreen. CI runs build + typecheck + test on Node 18/20/22.
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.
- 4d ago First seen · 84 lines · 930 tokens per session scan A 450d2d189dd2
fitness-tools AGENTS.md is an instructions file published in the GitHub repository almostjacked/fitness-tools (1 stars, last pushed 1mo ago), licensed MIT. It adds 930 tokens to every session, about $0.0047 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 instructions, from other repositories
withings-mcp CLAUDE.md
Instructions for akutishevsky/withings-mcp, covering claude.md, general rules, project overview, development commands and running.
icuvisor CLAUDE.md
Claude Code instructions for ricardocabral/icuvisor, covering claude.md, what this project is, authoritative documents, hard rules and project layout.
gccli CLAUDE.md
Claude Code instructions for bpauli/gccli, covering claude.md, project overview, build & quality commands, architecture and key packages.
FreeReps CLAUDE.md
Instructions for meltforce/FreeReps, covering freereps, gotchas, repository & ci/cd, data source documentation and repo documents.
garmin-connect-mcp AGENTS.md
Instructions for eddmann/garmin-connect-mcp: Prefer make targets over direct commands. Run make help to see available targets.
polar-flow-server CLAUDE.md
Claude Code instructions for StuMason/polar-flow-server, covering claude.md, project overview, development commands, install dependencies and start postgresql (required for local development).