A repository-specific guide for adding or changing tools in coach-mcp, an MCP server for Garmin-related coaching data. It covers the required code structure, safety labels, tests, storage, documentation, and end-to-end checks.

Use it when creating, renaming, combining, or changing an MCP tool in coach-mcp, including changes to snapshots or data pushing.

It prevents a new tool from missing the project’s required tests or making inaccurate claims about whether it reads or changes data. It also addresses consistent handling of dates and errors.

How snoozelieb/coach-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to snoozelieb/coach-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.

Copy the file

curl -O https://raw.githubusercontent.com/snoozelieb/coach-mcp/main/.claude/skills/new-tool/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/snoozelieb/coach-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/new-tool/github.svg)](https://agentmods.dev/skills/snoozelieb/coach-mcp/new-tool)

Your own site

<a href="https://agentmods.dev/skills/snoozelieb/coach-mcp/new-tool"><img src="https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/new-tool/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/snoozelieb/coach-mcp/new-tool"><img src="https://agentmods.dev/badge/skills/snoozelieb/coach-mcp/new-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 886 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00067	$0.00886
Opus 5	$0.00034	$0.00443
Sonnet 5	$0.00013	$0.00177
Haiku 4.5	$0.00007	$0.00089

Measured 10d ago against content hash 4125299567bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

new-tool 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 10d 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.

.claude/skills/new-tool/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding an MCP tool to coach-mcp

The contract suites make every step below mandatory — skipping one fails CI by design, so work down the list.

The checklist

Parsing first. Put pure, no-I/O parsing in coach/parsers.py (or the relevant module). Session/sport vocabulary comes from coach/taxonomy.py — never invent type strings.
Tool in coach/tools/. @mcp.tool(annotations={...}) — every tool MUST declare readOnlyHint/destructiveHint/idempotentHint/openWorldHint. Return structured dicts; fail gracefully with {'error': str(e)} after logger.exception() — always except Exception:, never a bare except: (it swallows KeyboardInterrupt/SystemExit). Writes go through coach.storage (atomic + locked). A tool with side effects (like the snapshot's ingestion) must NOT claim readOnlyHint.
Classify it in tests/test_annotations.py — the inventories are explicit; an unclassified tool fails the suite.
Clock discipline. If the tool reads the clock, resolve today/now ONCE at the tool boundary and thread today: date through helpers. Add the (file, function) pair to the tests/test_clock_discipline.py allowlist with a justification — stale allowlist entries also fail.
Tests. Happy + error paths through FakeGarminClient (tests/conftest.py) + sandbox_data_dir (seed inputs into the sandbox, assert on persisted output). Route Garmin traffic with patch_garmin_everywhere(monkeypatch, client); per-endpoint failures via overrides={'get_sleep_data': Exception('down')}. Never hand-roll Garmin mocks. Async tools: pytest-asyncio auto mode + the mock_ctx fixture. Use relative dates (date.today() + timedelta(...)) — hardcoded dates rot. Import coach modules as import coach.planner as planner, never from coach.planner import f — monkeypatch targets go stale otherwise.
Run python -m pytest -v.

When the change is bigger than one tool

Snapshot or push behavior → extend the golden-schema e2e tests (tests/test_e2e_snapshot.py, tests/test_e2e_push.py).
Renaming or consolidating tools → renames are atomic. Doc hygiene in tests/test_consolidations.py bans stale tool names in CLAUDE.md, prompts, the doctrine resource, SERVER_INSTRUCTIONS, and daily_loop; the old→new table in CLAUDE.md's "Removed / consolidated tools" section must document every rename, and that section must stay ahead of ## Commands.
New Garmin endpoint → add the call shape to tests/test_garmin_contract.py and a realistic response shape to FakeGarminClient (list-vs-dict fidelity is load-bearing).
Doctrine-relevant behavior → update coach/resources.py (coach://coaching/doctrine) and, if a hard mandate changes, SERVER_INSTRUCTIONS in coach/mcp_app.py — keep it under the 2,000-char budget (tests/test_server_instructions.py). Never add doctrine to CLAUDE.md.

Read the full file on GitHub · 64 lines

Changes

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.

10d ago First seen · 64 lines · 67 tokens per session scan A 4125299567bf

Subscribe to this mod's changes

new-tool is a skill published in the GitHub repository snoozelieb/coach-mcp (2 stars, last pushed 14d ago), licensed MIT. It adds 67 tokens to every session and 886 once invoked, about $0.0003 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.

Backend and APIs Building agents

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens

telnyx-messaging-hosted-curl

Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.

team-telnyx/ai · 45 tokens

coach-mcp: Skill for Claude Code