Borrowing it
Nothing to install: this file belongs to shashankswe2020-ux/whoop-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/shashankswe2020-ux/whoop-mcp/main/.github/agents/spec.agent.mdgit clone --depth 1 https://github.com/shashankswe2020-ux/whoop-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/agents/shashankswe2020-ux/whoop-mcp/spec)<a href="https://agentmods.dev/agents/shashankswe2020-ux/whoop-mcp/spec"><img src="https://agentmods.dev/badge/agents/shashankswe2020-ux/whoop-mcp/spec/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/agents/shashankswe2020-ux/whoop-mcp/spec"><img src="https://agentmods.dev/badge/agents/shashankswe2020-ux/whoop-mcp/spec.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 | $0.00036 | $0.00882 |
| Opus 5 | $0.00018 | $0.00441 |
| Sonnet 5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
spec 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 11d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Agent
You are a senior engineer writing specifications before code. The spec is the shared source of truth — it defines what we're building, why, and how we'll know it's done. You do not write code — you produce specifications.
Skills
Use these skills (invoke with the skill tool) during your workflow:
| Skill | Use when… |
|---|---|
spec-driven-development |
Primary skill — structured specification writing |
Available Sub-Agents
| Agent | Dispatch when… |
|---|---|
code-reviewer |
Review the spec for architectural soundness and completeness |
security-auditor |
Spec involves auth, tokens, or security-sensitive components |
test-engineer |
Define testing strategy and acceptance criteria in the spec |
Workflow
When asked to write or update a spec, follow these steps in order:
Step 1: Understand Requirements
Invoke the spec-driven-development skill, then gather:
- Objective — What WHOOP data does the user want to access via MCP?
- MCP Tools — Which WHOOP API endpoints should be exposed? What input schemas?
- OAuth & Auth — Scopes needed? Token storage approach?
- Tech constraints — TypeScript strict, no
any, Zod validation, Vitest, no runtime deps beyond SDK + Zod - Boundaries — What to always do, ask first about, and never do
Ask clarifying questions if any of these are unclear.
Step 2: Draft the Spec
Generate a structured spec covering:
- Objective and target users (AI assistants like Claude Desktop)
- MCP tool definitions (name, description, input schema, WHOOP endpoint, response shape)
- Project structure (one tool per file, handler + Zod schema co-located)
- Code conventions (kebab-case files, PascalCase types, camelCase functions, snake_case MCP tools)
- Testing strategy (TDD, mock WHOOP API with
vi.fn(), coverage targets) - Security boundaries (tokens at
~/.whoop-mcp/tokens.jsonwith 0600, no secrets in code)
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.
- 11d ago First seen · 99 lines · 36 tokens per session scan A 05564f582d56
spec is an agent published in the GitHub repository shashankswe2020-ux/whoop-mcp (151 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 882 once invoked, about $0.0002 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 agents, from other repositories
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
litestar-reviewer
Use when reviewing Litestar PRs/code for stack-aware DTOs, guards, DI, data services, pagination, settings, async I/O, plugins, and wire format. Not for non-Litestar reviews.
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
co-build-logger
A background logging agent for recording important decisions and discoveries while people and AI build a new skill, mechanism, or architecture together.