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/chrisdoc/hevy-mcp/agents-mdgit clone --depth 1 https://github.com/chrisdoc/hevy-mcpWrote 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/chrisdoc/hevy-mcp/agents-md)<a href="https://agentmods.dev/instructions/chrisdoc/hevy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/chrisdoc/hevy-mcp/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 | $0.03701 | $0.03701 |
| Opus 5 | $0.01851 | $0.01851 |
| Sonnet 5 | $0.00740 | $0.00740 |
| Haiku 4.5 | $0.00370 | $0.00370 |
Grade A, and why
hevy-mcp 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 today.
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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for hevy-mcp
Read this file before changing the repository. Keep this file focused on agent-only rules; use the linked documents and repository configuration as the source of truth for detailed commands and changing facts.
Learning more about Effect
This repository uses the Effect Typescript library.
Before writing any Effect code, first read node_modules/effect/AGENTS.md
completely, and follow the links in the file when required.
If you need to learn more about particular Effect apis and concepts that the
guide doesn't cover, search through the source code in node_modules/effect/src.
Start in a fresh worktree
-
Inspect the checkout before touching it:
git status --short --branch -
Fetch the current base and create a dedicated feature branch/worktree from it:
git fetch origin main git worktree add -b <type>/<topic> ../hevy-mcp-<topic> origin/mainUse a branch type such as
feat,fix,docs,test,refactor, orchore. Preserve existing user changes; ask before proceeding if creating the worktree would risk them. -
Implement and validate in the new worktree. The work is ready for review only when the branch is based on
origin/main, is notmain, and the original checkout remains untouched.
Never push directly to main. Use Conventional Commits (feat:, fix:,
docs:, test:, refactor:, build:, ci:, chore:, or style:) and keep
Git hooks enabled. Fix hook failures instead of bypassing them.
Git safety in tests
- Never write tests that invoke Git, execute
gitcommands, or mutate Git repositories or Git configuration. Use pure logic and ordinary filesystem fixtures instead. - Never create, configure, or persist test Git identities such as
user.name,user.email,GIT_AUTHOR_*, orGIT_COMMITTER_*.
Source-of-truth pointers
CONTRIBUTING.mdowns development setup, Node policy, Worker operations, release policy, and the required validation baseline. Read the relevant section before that class of change.docs/test-lanes.mdowns named test lanes. Prefer thepnpm run test:*aliases over copying raw Vitest selectors.repository/topology.jsonowns workspace boundaries and release bundles.package.jsonowns the current command names. Inspect it instead of copying command details into new documentation.- Use the GitHub MCP server for GitHub operations. Use
ghonly when the GitHub MCP server cannot complete the operation because of a token problem.
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.
- today Changed · +145 lines · +1,251 tokens per session 3a7c2f7502ab
- 4d ago First seen · 239 lines · 2,450 tokens per session scan A 380fb4621337
hevy-mcp AGENTS.md is an instructions file published in the GitHub repository chrisdoc/hevy-mcp (451 stars, last pushed today), licensed MIT. It adds 3,701 tokens to every session, about $0.0185 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 2026-08-30.
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.
FreeReps CLAUDE.md
Instructions for meltforce/FreeReps, covering freereps, gotchas, repository & ci/cd, data source documentation and repo documents.
claude-hevy-coach CLAUDE.md
Claude Code instructions for jmilinovich/claude-hevy-coach, covering you are this user's strength coach, before anything: make sure the machine works, first conversation: onboard the athlete, every session: the coaching loop and standing rules.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.