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/matisdsp/fartlek/claude-mdgit clone --depth 1 https://github.com/matisdsp/fartlekWrote 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/matisdsp/fartlek/claude-md)<a href="https://agentmods.dev/instructions/matisdsp/fartlek/claude-md"><img src="https://agentmods.dev/badge/instructions/matisdsp/fartlek/claude-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 5.1 | $0.00941 | $0.00941 |
| Opus 5 | $0.00470 | $0.00470 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
fartlek CLAUDE.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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fartlek — Garmin MCP server
A coach's morning report from your Garmin data, for any LLM via MCP. Open-source project. The authoritative spec is docs/DESIGN.md; the phase plan is ROADMAP.md.
Language: English only. This is a public open-source repo — write everything in English: code, identifiers, comments, docstrings, user-facing strings, commit messages (subject and body), and docs. The sole exception is quoted foreign-language content that is itself the subject under test (e.g. the French eval task in docs/EVAL.md that checks numbers survive translation).
Picking up the project? Start with docs/HANDOFF.md — current state, verified facts, invariants, and the traps that cost time. Phases 0–2 are done (v0.2.0 on PyPI); Phase 3 is next.
Git discipline — commit as you go
Commit incrementally, as soon as a coherent change is done and verified. Do not accumulate a large uncommitted working tree.
- One logical change = one commit (a module, a new tool, a fix — not "misc").
- Verify before committing (run the relevant tests; for the MCP server, the standalone JSON-RPC check below).
- Concise imperative messages, scoped:
analytics: add PMC engine,store: fix WAL busy timeout. - Never commit secrets or tokens (
~/.fartlek/,garmin_tokens.json).
Architecture
fartlek/health/— Garmin data access.ports.py(GarminPort protocol) →adapters/garmin_connect.py(garminconnectlib, sync calls inasyncio.to_threadbehind a lock + cross-process fcntl token lock) →service.py(field filtering). Consumers go through HealthService, never the adapter.fartlek/mcp_server/server.py— FastMCP stdio server. stdout is reserved for JSON-RPC; log to stderr only.fartlek/cli.py—fartlek auth/doctor/accounts/reset. The only place credentials are typed.fartlek/paths.py— filesystem layout (~/.fartlek/, overrideFARTLEK_HOME; tokens overrideGARMINTOKENS).- Phase 0 adds:
fartlek/store/(per-account SQLite),fartlek/sync/(fetch + digestion engine),fartlek/analytics/(deterministic metrics),fartlek/render/(budgeted verdict renderer). Specs: DESIGN.md §3 and §5.
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.
- 5d ago First seen · 53 lines · 941 tokens per session scan A f3063d21a53b
fartlek CLAUDE.md is an instructions file published in the GitHub repository matisdsp/fartlek (0 stars, last pushed 18d ago), licensed Apache-2.0. It adds 941 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.