Borrowing it
Nothing to install: this file belongs to sla1k/smart-gym-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sla1k/smart-gym-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/sla1k/smart-gym-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/sla1k/smart-gym-mcp/agents-md)<a href="https://agentmods.dev/instructions/sla1k/smart-gym-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sla1k/smart-gym-mcp/agents-md/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/instructions/sla1k/smart-gym-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sla1k/smart-gym-mcp/agents-md.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 | $0.00843 | $0.00843 |
| Opus 5.5 | $0.00337 | $0.00337 |
| Sonnet 5.5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
smart-gym-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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project knowledge lives in shared docs — read them, don't rediscover:
DESIGN.md— start here: status table, verified facts (settled — do not re-derive or re-litigate them), architecture invariants, decision logdocs/superpowers/specs/2026-10-05-api-client-design.md— source of truth for the API client (module layering §5, tool surface §6, sections §10);specs/holds the superseded DB-era specsFEATURES.md— backlog
Working rules for this repo
- Follow the architecture invariants in DESIGN.md exactly — especially: thin tools, every write
through
service.RoutineService, every edit of an existing routine throughdiff_routine. - The SmartGym account is the user's live personal training data. Live checks only on
ZZ-prefixed throwaway routines, with the user confirming on the iPhone. Snapshots land in~/.smartgym-mcp/backups/<ts>/. - Before trusting a NEW kind of server write, capture the app doing it first (golden fixture in
tests/fixtures/api/) instead of assuming the wire shape. - Tests never touch the network or the account — use the fixtures and
tests/fakes.FakeClient. maintakes no direct pushes: every change lands through a PR that is up to date withmainand has a greencicheck, merged by rebase (linear history, no merge commits).
Branches and PRs
- One task per branch, worktree and PR.
- Before the first push, name the branch
type/short-description: type is one offeat,fix,docs,ci,refactor,test,chore; lowercase, words joined by hyphens; no agent or tool prefix. CI fails other names. - Name the branch before opening the PR; renaming it afterwards, locally or on GitHub, closes or orphans the PR.
- Before pushing, run
uv run ruff check src tests scripts/smoke_stdio.py,uv run ruff format --check src tests scripts/smoke_stdio.py,uv run mypyanduv run pytest— the same steps as CI.scripts/smoke_stdio.pyotherwise runs only in the release build after the merge;scripts/spike/holds throwaway capture scripts and stays unchecked. - The PR description says what changed, why, and how it was verified.
- Update the branch from
mainbefore merging; rebase merge only.
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 Changed · -2 tokens per session b6968ce09373
- 6d ago Changed · +3 lines · +82 tokens per session 3c9c689ad972
- 10d ago First seen · 51 lines · 763 tokens per session scan A 55363e208cbd
smart-gym-mcp AGENTS.md is an instructions file published in the GitHub repository sla1k/smart-gym-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 843 tokens to every session, about $0.0034 per session on Opus 5.5. 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 2026-10-20.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.