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/samaxbytez/freeagent-mcp/claude-mdgit clone --depth 1 https://github.com/samaxbytez/freeagent-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/samaxbytez/freeagent-mcp/claude-md)<a href="https://agentmods.dev/instructions/samaxbytez/freeagent-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/samaxbytez/freeagent-mcp/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 5.1 | $0.00871 | $0.00871 |
| Opus 5 | $0.00436 | $0.00436 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
freeagent-mcp 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project guidance for Claude Code working in this repository.
What this is
freeagent-mcp-server — an MCP (Model Context Protocol) server that exposes the
FreeAgent accounting API as tools for LLM clients.
TypeScript, ESM, published to npm, driven over stdio.
Architecture
src/
├── index.ts # Entry point: builds the McpServer, wires the client, registers every tool group
├── auth.ts # OAuth2 flow, token storage (~/.freeagent-mcp/tokens.json) and refresh
├── client.ts # FreeAgentClient — HTTP wrapper around fetch (get/postJson/putJson/deleteReq)
├── utils.ts # Shared helpers: jsonResponse, errorResponse, logToolCall, buildParams, safeId, constants
└── tools/ # One file per FreeAgent resource, each exporting registerXxxTools(server, client)
Tests are co-located as *.test.ts and run with vitest.
Tool pattern
Every resource file exports a registerXxxTools(server, client) function and
registers tools with server.tool(...) (or server.registerTool(...)). Each
handler:
- Calls
logToolCall(name, args)first. - Uses the
clientto hit the API (paths are relative, e.g.`/contacts/${id}`). - Wraps the result in
jsonResponse(data)and errors inerrorResponse(err). - Uses
buildParams(...)for query strings.
IDs are interpolated into request paths, so every ID parameter MUST use the
safeId schema from utils.ts (z string matching /^[a-zA-Z0-9_-]+$/), not a
plain z.string(). See any freeagent_get_* tool for the canonical shape.
To add a tool, use the /add-tool command — it scaffolds handler, registration,
and test following this pattern.
Security conventions (this repo's threat model is indirect prompt injection)
- IDs → always
safeId(blocks path traversal via ID fields). client.tsrejects absolute URLs /../and verifies the resolved URL's origin matches the API base — never weaken this; it prevents the bearer token being sent off-origin.- Browser launch uses
execFile(neverexec/shell) andexplorer.exeon Windows — never reintroduce shell interpolation of a URL. - Token file is written
0o600in a0o700directory. Never log tokens.
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 · 74 lines · 871 tokens per session scan A 6fa8651c46f0
freeagent-mcp CLAUDE.md is an instructions file published in the GitHub repository samaxbytez/freeagent-mcp (4 stars, last pushed 10d ago), licensed MIT. It adds 871 tokens to every session, about $0.0044 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
carrier-accounting-mcp CLAUDE.md
Claude Code instructions for pramodmisra/carrier-accounting-mcp, covering carrier accounting mcp — claude code context, critical data protection rules, project overview, architecture and repository structure.
ledgerlink-mcp CLAUDE.md
Claude Code instructions for bpmj-martin/ledgerlink-mcp, covering project: ledgerlink mcp, current state, recent changes, architecture and tech stack.
counterpoise-ledger CLAUDE.md
Instructions for jeffjjohnston/counterpoise-ledger, covering claude.md, project overview, development commands, essential commands and testing.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
finance-automation-portfolio CLAUDE.md
Instructions for sophonfinance-wq/finance-automation-portfolio, covering sophon finance systems — portfolio repo, orient in 30 seconds, use the skills — don't re-derive and house rules.
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.