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/reyemtech/mcp-canada/claude-mdgit clone --depth 1 https://github.com/ReyemTech/mcp-canadaWrote 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/reyemtech/mcp-canada/claude-md)<a href="https://agentmods.dev/instructions/reyemtech/mcp-canada/claude-md"><img src="https://agentmods.dev/badge/instructions/reyemtech/mcp-canada/claude-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 | $0.04682 | $0.04682 |
| Opus 5 | $0.02341 | $0.02341 |
| Sonnet 5 | $0.00936 | $0.00936 |
| Haiku 4.5 | $0.00468 | $0.00468 |
Grade A, and why
mcp-canada CLAUDE.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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Unit tests (fast, mocked — default)
uv run pytest
# Single test file
uv run pytest src/mcp_canada/modules/bank_of_canada/__tests__/test_tools.py -x -v
# Single test
uv run pytest src/mcp_canada/modules/bank_of_canada/__tests__/test_tools.py::TestBocGetExchangeRates::test_returns_exchange_rates -x
# Integration tests (live APIs, ~2min)
uv run pytest tests/integration/ -v -m integration --timeout=120
# Coverage (must be ≥95%)
uv run pytest --cov=src/mcp_canada --cov-fail-under=95
# Start server
uv run mcp-canada # stdio
uv run mcp-canada --transport sse --port 8000 # SSE
uv run mcp-canada --transport http --port 8000 # Streamable HTTP
uv run mcp-canada --modules bank_of_canada,recalls # selective
# Type check & lint
uv run pyright
uv run ruff check src/ tests/
Architecture
FastMCP 3.2.x with FileSystemProvider auto-discovery. Drop a module folder into src/mcp_canada/modules/ — it registers automatically.
BM25SearchTransform hides all tools behind discover_tools + call_tool. Agents see 3 always-visible tools; the ~50 underlying tools are found via BM25 search.
Lifespan creates a shared httpx.AsyncClient. Supports stdio, SSE, and Streamable HTTP.
Module Pattern (7 files + tests)
Every module in src/mcp_canada/modules/{name}/:
| File | Purpose |
|---|---|
__init__.py |
MODULE_NAME and MODULE_DESCRIPTION |
constants.py |
BASE_URL, RATE_GROUP, RATE_LIMIT, CACHE_TTL, mappings |
schemas.py |
Pydantic v2 models — always flat |
client.py |
Async functions returning (data, was_cached) tuples |
tools.py |
@tool functions (standalone, NOT @mcp.tool) |
prompts.py |
@prompt functions — guided workflows + quick lookups |
resources.py |
@resource functions — catalogs, docs, templates |
__tests__/ |
conftest.py, test_client.py, test_tools.py, test_prompts_resources.py |
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 · 161 lines · 4,682 tokens per session scan A 9a679c043460
mcp-canada CLAUDE.md is an instructions file published in the GitHub repository ReyemTech/mcp-canada (59 stars, last pushed 11d ago), licensed MIT. It adds 4,682 tokens to every session, about $0.0234 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
jobxhunter AGENTS.md
AGENTS.md instructions for soheilfallah/jobxhunter, covering agents.md, where the content comes from, start here, the pipeline and running the deterministic scripts.
ihalent copilot-instructions.md
Instructions for gulmezeren2-byte/ihalent, covering copilot instructions — ihalent, build, test, lint, architecture and conventions.
govuk-mcp CLAUDE.md
Instructions for paulieb89/govuk-mcp, covering claude.md, project, tools, resources (govuk:// uri templates) and commands.
product-idea-excavator AGENTS.md
Instructions for derrickgong87/product-idea-excavator, covering agents.md, 项目使命, 目标 skill, 触发场景 and 角色定位.
govuk-mcp AGENTS.md
Instructions for paulieb89/govuk-mcp, covering agents.md — govuk-mcp, repo shape, deploy, version bump and standard routes (must always be present).
it-contractors-skills CLAUDE.md
Instructions for AlexTeplovCPA/it-contractors-skills, covering claude.md - claude adapter for it-contractors-skills, repository purpose, repository scope, core strategy and broad intake skills.