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/antvsl/oura_mcp/agents-mdgit clone --depth 1 https://github.com/AntVsl/oura_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/antvsl/oura_mcp/agents-md)<a href="https://agentmods.dev/instructions/antvsl/oura_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/antvsl/oura_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 5.1 | $0.00896 | $0.00896 |
| Opus 5 | $0.00448 | $0.00448 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
oura_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 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
This file applies to the entire repository. It is the source of truth for
Codex and other coding agents; more-specific AGENTS.md files would override
it for their directory.
Mission and boundaries
my-oura-mcp is a privacy-sensitive MCP server for Oura Ring data. Preserve
the same public tool schema and response shape for every client:
- Claude Code and Codex use local
stdioor an authenticated HTTP endpoint. - Claude.ai and ChatGPT use the public
streamable-httpendpoint and OAuth. - The server summarizes consumer health data; do not add diagnosis, treatment, or medical claims to tools, prompts, skills, or documentation.
Never print, commit, or put real values from .env, .oura/, bearer headers,
or OAuth tokens into tests, documentation, fixtures, logs, or issue text.
Do not broaden OURA_OAUTH_ALLOWED_REDIRECT_ORIGINS without an explicit,
reviewed client origin. It is an OAuth redirect allowlist, not a convenience
setting.
Repository map
| Path | Responsibility |
|---|---|
src/my_oura_mcp/ |
Server, OAuth, Oura client, cache, output shaping |
tests/ |
Offline unit and MCP protocol tests |
skills/oura/ |
Client-neutral Oura analysis recipes; keep medical boundary |
skills/oura-mcp-maintenance/ |
Focused maintenance skill for this repository |
docs/ |
Deployment, design decisions, and agent workflow |
server.json |
MCP Registry manifest; version must match pyproject.toml |
compose*.yml, Dockerfile |
Production HTTP deployment |
Read the relevant module and its tests before changing behavior. Prefer a small focused patch; do not reformat unrelated files.
Standard workflow
- Inspect
git status --shortfirst and preserve unrelated working-tree changes. - State the owned files and acceptance criteria in the task brief from
docs/agents/task-template.mdfor any change larger than a one-file fix. - Add or update a regression test whenever externally observable behavior, OAuth policy, parsing, cache behavior, packaging, or documentation contract changes.
- Run the narrow test first, then the full gate:
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 · 92 lines · 896 tokens per session scan A 1d48fb4707a0
oura_mcp AGENTS.md is an instructions file published in the GitHub repository AntVsl/oura_mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 896 tokens to every session, about $0.0045 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
whoop-mcp AGENTS.md
Instructions for davidmosiah/whoop-mcp, covering agent development notes, scope, commands and rules.
oura-mcp CLAUDE.md
Claude Code instructions for Rajskij/oura-mcp, covering claude.md, current phase: 2 — showcase (self-host distribution), stack, commands and rules.
aihw-mcp CLAUDE.md
Claude Code instructions for Bigred97/aihw-mcp, covering aihw-mcp, source, curated datasets (8), repo-specific module set and repo-specific gotchas.
whoop-mcp AGENTS.md
AGENTS.md instructions for AshwanthramKL/whoop-mcp, covering agents.md, 1. project shape in one paragraph, 2. before you touch anything, 3. file layout and 4. the error envelope is non-negotiable.
supstack-cli CLAUDE.md
Claude Code instructions for DrBaher/supstack-cli, covering supstack cli — conventions, the capability pattern (the one rule that matters), to add a capability, architectural decisions and commands.
vitamind CLAUDE.md
Claude Code instructions for JaviMaligno/vitamind, covering claude.md, project overview, development commands, architecture and next.js app router (app/).