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/samarpassey/maple-procure/claude-mdgit clone --depth 1 https://github.com/samarpassey/maple-procureWrote 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/samarpassey/maple-procure/claude-md)<a href="https://agentmods.dev/instructions/samarpassey/maple-procure/claude-md"><img src="https://agentmods.dev/badge/instructions/samarpassey/maple-procure/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 | $0.00675 | $0.00675 |
| Opus 5 | $0.00338 | $0.00338 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
maple-procure 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 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MapleProcure
An MCP server over Canada's public tender and award data (CanadaBuys). Python, mcp 2.0.0,
SQLite, FastAPI host for streamable HTTP.
Commands
| Command | What |
|---|---|
make install |
uv sync --extra dev |
make ingest |
Download CanadaBuys CSVs → build data/maple.sqlite |
make test |
pytest |
make lint / make fmt |
ruff check / ruff format+fix |
make serve-stdio |
MCP over stdio |
make serve-http |
FastAPI + streamable HTTP on :8000 |
Invariants — do not break these without an entry in docs/DECISIONS.md
- Never commit data. No CSVs, no
.sqlite. A clean clone reproduces withmake install && make ingest && make test. Onlytests/fixtures/*.csvis committed. - Parameterised SQL only. No string interpolation into queries, ever.
- Every tool result carries provenance —
as_of,source_file,row_count. No exceptions. - Contact details are off by default. Buyer names, emails and phones live in
tender_contactsand are returned only under thepiiscope with an explicit argument. - Never claim a capability that isn't in the code today — in the README, the tool
descriptions, or anywhere else. If it ships, it works; if it doesn't work, it's in
KNOWN_LIMITATIONS.md. - Docs change in the same commit as the code they describe. A stale map is worse than no map.
- No Python file over 250 lines — enforced by
tests/test_file_sizes.py. When a module approaches the cap, that is the signal to split it, not to raise the cap. Declare a thing once: fields live inmapping.pyand the DDL, INSERT, and row builders all derive from them.
Read these when
| File | When |
|---|---|
PROGRESS.md |
Start of every session. Component states and next step. |
PLAN.md |
Before starting a component. Scope and the order scope gets dropped in. |
docs/DATA.md |
Touching ingest, columns, or anything about the source files. |
docs/SPEC-NOTES.md |
Touching the MCP server, transports, auth, or the export flow. |
docs/DECISIONS.md |
When a choice feels arbitrary — it probably was decided already. |
KNOWN_LIMITATIONS.md |
Before writing anything that claims what the server can do. |
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 First seen · 52 lines · 675 tokens per session scan A 04f56f3c162c
maple-procure CLAUDE.md is an instructions file published in the GitHub repository samarpassey/maple-procure (0 stars, last pushed 19d ago), licensed MIT. It adds 675 tokens to every session, about $0.0034 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
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
mcpelevator AGENTS.md
Instructions for pacnpal/mcpelevator, covering commands, architecture and conventions.
lantern AGENTS.md
Instructions for lanseqingling/lantern, covering agents.md, project, commands, repository guide and architecture boundaries.
elicitly AGENTS.md
AGENTS.md instructions for elicitly/elicitly: This is the open-source Elicitly Free Edition: packages/elicitly (the local stdio MCP server published as elicitly) and packages/tools (the embeddable @elicitly/tools toolkit). The hosted Pro Edition lives in a separate private repository — nothing here may depend on it or…
agentcloud AGENTS.md
AGENTS.md instructions for premhiru/agentcloud, covering agentcloud engineering rules and this is not the next.js you know.
1cent AGENTS.md
AGENTS.md instructions for maxzoa/1cent, a project described as: Pay-per-call URL intelligence for AI agents via MCP and x402 USDC on Base Mainnet.