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/damosullivan/daft-mcp/agents-mdgit clone --depth 1 https://github.com/damosullivan/daft-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/damosullivan/daft-mcp/agents-md)<a href="https://agentmods.dev/instructions/damosullivan/daft-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/damosullivan/daft-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 | $0.00784 | $0.00784 |
| Opus 5 | $0.00392 | $0.00392 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
daft-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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Compact guidance for OpenCode sessions working in this repo.
Stack
- Python 3.10+, managed with uv.
uv.lockis the source of truth — alwaysuv sync/uv run, never edit the lockfile by hand. - Build backend is hatchling with
allow-direct-references = true(pyproject.toml), required becausedaftlistingsis pinned to the gitmasterbranch — not PyPI. The PyPI release (2.0.5) has aUser-Agentbug; master has the fix. Do not "fix" this to a PyPI version.
Running
uv sync # install into .venv
uv run daft-mcp # run the server (stdio transport)
uv run python -m daft_mcp.server # equivalent
Verification
There is no test suite. Verify changes with:
uv run mypy src/ # type check
npx @modelcontextprotocol/inspector uv run daft-mcp # live tool test
After touching tool signatures or behaviour, exercise the tool through the MCP Inspector before considering the change done.
Architecture
Single-file server: src/daft_mcp/server.py. Everything lives there.
- One
FastMCP("daft")instance; each@mcp.tool()decorator registers a tool. Entry pointmain()callsmcp.run(transport="stdio"). __init__.pyre-exportsmainsopython -m daft_mcp.serverand thedaft-mcpconsole script both work._enum_from_string(enum_cls, value)is the forgiving resolver for everydaftlistingsenum (SearchType,PropertyType,Facility,SortType,Ber,AddedSince). It lowercases and normalises-/space →_, matching by.valuefirst then.name. All tool string params flow through it._format_listing()reads listing attributes defensively — every field access is wrapped intry/exceptbecausedaftlistingsraises on missing fields. Preserve this pattern when adding fields.
Critical gotcha: stdout is the MCP transport
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 · 74 lines · 784 tokens per session scan A d75a46f56b40
daft-mcp AGENTS.md is an instructions file published in the GitHub repository damosullivan/daft-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 784 tokens to every session, about $0.0039 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.