Borrowing it
Nothing to install: this file belongs to netcare-io/fitnesse-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.
curl -O https://raw.githubusercontent.com/netcare-io/fitnesse-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/netcare-io/fitnesse-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/netcare-io/fitnesse-mcp/agents-md)<a href="https://agentmods.dev/instructions/netcare-io/fitnesse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/netcare-io/fitnesse-mcp/agents-md/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.
<a href="https://agentmods.dev/instructions/netcare-io/fitnesse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/netcare-io/fitnesse-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01037 | $0.01037 |
| Opus 5.5 | $0.00415 | $0.00415 |
| Sonnet 5.5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
fitnesse-mcp AGENTS.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **HTTP to FitNesse** goes through urllib; tests replace it with fakes that record requests and How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working on this repository. Users of the server: see README.md.
What this is
fitnesse-mcp is a FastMCP server that exposes FitNesse's REST responders as MCP tools. The
whole server is one module, server.py; the tests are in tests/.
- FastMCP is pinned exactly (
fastmcp==4.1.6in pyproject.toml): it has broken things in minor releases. Bump it only on purpose and run the full test suite after. - Python 3.12+; CI tests 3.12 and 3.13.
- The KDTA debug tools (
fitnesse_debug_*,fitnesse_table_*) need netcare's FitNesse fork, which adds thedebugTest/debugTableresponders. A plain FitNesse does not have them. Features of newer forks get a fallback for older ones (look for "older fork" / "mod #…" inserver.py).
Commands
pip install -e ".[dev]"
pytest # the whole suite, ~40 s
pytest tests/test_debug.py -q # debug tools only
python scripts/tools_list.py # regenerate docs/tools.md after changing any tool
tests/test_tools_doc.py fails while docs/tools.md does not match the tools.
How the code is organised
- Configuration is read at import.
FITNESSE_TOOLSETSis required and decides which tools exist. Tests that need other settings set the environment andimportlib.reload(server)(see_reloadand thedebug_envfixture intests/test_debug.py;tests/conftest.pysets the defaultall). - Tool visibility goes by tags. Each tool has one mode tag (
read,write,test) and optionally an area (debug,complete). Extra env gates (FITNESSE_FILES_ROOT,FITNESSE_ALLOW_SHUTDOWN,FITNESSE_ALLOW_ACCOUNT_ADMIN) hide tools completely. - Debug session state lives in
_DebugState, per FitNesse login and URL (headers auth mode lets each HTTP request bring its own). It is in memory only. - HTTP to FitNesse goes through urllib; tests replace it with fakes that record requests and return canned answers. No test needs a running FitNesse.
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.
- today First seen · 73 lines · 1,037 tokens per session scan A a0849e0be5fc
fitnesse-mcp AGENTS.md is an instructions file published in the GitHub repository netcare-io/fitnesse-mcp (1 stars, last pushed today), licensed MIT. It adds 1,037 tokens to every session, about $0.0041 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-10.
fitnesse-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fitnesse-mcp AGENTS.mdnetcare-io/fitnesse-mcp | Instructions file | 1 | today | MIT | A | 1,037 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |