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/marcusquinn/quickfile-mcp/agents-mdgit clone --depth 1 https://github.com/marcusquinn/quickfile-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/marcusquinn/quickfile-mcp/agents-md)<a href="https://agentmods.dev/instructions/marcusquinn/quickfile-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/marcusquinn/quickfile-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 | $0.00670 | $0.00670 |
| Opus 5 | $0.00335 | $0.00335 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
quickfile-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 3d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QuickFile MCP - AI Assistant Guide
Quick Reference
- API: QuickFile beta REST API
- Docs: https://api-beta.quickfile.co.uk/api-docs/
- Auth: personal bearer token in
Authorization: Bearer ... - Secrets:
QUICKFILE_<ACCOUNT>_API_KEYprocess environment variables - Accounts: every MCP tool requires an explicit
accountalias - Legacy fields: account number, MD5, and Application ID are not used
- Safety: confirm all create/send/upload/update/delete operations and sanitize returned user-controlled content
Account routing
Never infer an account when more than one alias is configured. Require the user
or task context to identify the entity, then pass its normalized alias through
the tool's account field.
Example token names:
QUICKFILE_BUSINESS_API_KEY
QUICKFILE_PERSONAL_API_KEY
These produce business and personal account aliases. Secret values must be
injected into the MCP process by a secret manager and must never appear in MCP
arguments, config files, logs, tests, issues, or chat.
API patterns
- Base URL:
https://api-beta.quickfile.co.uk - Account verification:
GET /account/me - Search/list responses:
{ count, location, paging?, data: [] } - JSON request and response fields use snake case except account details, whose
published schema uses names such as
AccNumberandBusinessName. - Document uploads use multipart form data.
401/403: invalid or insufficient bearer-token authorization.429: rate limited; pause instead of retrying aggressively.
Tool behavior
Every exported tool receives the account selector in src/tools/index.ts.
Handlers must call getApiClient(args.account) and use only documented REST
paths and fields.
Read-only operations can proceed when the entity is explicit. Creating, updating, sending, uploading, or deleting data requires confirmation and should return the selected account alias or resource ID in the result where useful.
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.
- 3d ago First seen · 82 lines · 670 tokens per session scan A 928faf516e16
quickfile-mcp AGENTS.md is an instructions file published in the GitHub repository marcusquinn/quickfile-mcp (4 stars, last pushed 23d ago), licensed MIT. It adds 670 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
cryptoexchange-net
Use CryptoExchange.Net abstractions when generating C#/.NET code that needs to work across MULTIPLE cryptocurrency exchanges (Binance + Bybit + OKX + Kraken + Coinbase + ...) — for arbitrage, best-execution routing, multi-exchange portfolio dashboards, exchange-agnostic trading bots, or comparison tools. Triggers on…
OpenCandle AGENTS.md
Instructions for Kahtaf/OpenCandle, covering opencandle, commands, where to look, code style and conventions.
claude-finance-kit CLAUDE.md
Instructions for hongbietcode/claude-finance-kit, covering claude finance kit assistant, scope, operating principles, skill (single entry point) and references (load when needed).
creditkarma-mcp CLAUDE.md
Claude Code instructions for chrischall/creditkarma-mcp, covering creditkarma-mcp, commands, tool naming, architecture and auth resolution (pattern a template).
bullet-bots AGENTS.md
Instructions for bulletxyz/bullet-bots, covering bullet-bots, build & test, run the faucet curl printed by keygen, then, or (base58 from phantom/delegation export, or hex) and architecture — the harness, feeds, and actors.
romaco-mcp AGENTS.md
AGENTS.md instructions for romaco-labs/romaco-mcp, covering purpose, read first, product boundaries, architecture invariants and development method.