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/guillaumegay13/fieldflow/agents-mdgit clone --depth 1 https://github.com/guillaumegay13/fieldflowWrote 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/guillaumegay13/fieldflow/agents-md)<a href="https://agentmods.dev/instructions/guillaumegay13/fieldflow/agents-md"><img src="https://agentmods.dev/badge/instructions/guillaumegay13/fieldflow/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 | $0.00760 | $0.00760 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
fieldflow 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Commit messages in this repo use short imperative summaries (e.g., `add proxy filter logging`). Group related changes together and include follow-up detail in the body only when necessary. Pull requests should describe b How it starts
The opening of the file, as written. The whole thing — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Core runtime code lives in fieldflow/, exported as the fieldflow package that builds FastAPI tooling on top of OpenAPI specs. MCP-specific utilities and the CLI wrapper stay in fieldflow_mcp/. Specs for local experimentation sit in examples/, while tests/ holds pytest-based coverage for the HTTP proxy and MCP integration. Tooling metadata such as pyproject.toml and requirements.txt define install targets and extras (.[dev], .[mcp]).
Current Product Scope
FieldFlow currently supports OpenAPI-described REST APIs exposed as HTTP tool endpoints and the same generated OpenAPI tools exposed through MCP. It does not yet wrap arbitrary existing MCP servers. If work moves toward existing MCP server proxying, keep it in a dedicated design/feature PR and prefer MCP tools with structured outputSchema.
Build, Test, and Development Commands
Bootstrap everything at once with python -m venv .venv && source .venv/bin/activate && python -m pip install --upgrade pip && python -m pip install -e '.[dev,mcp]'. Launch the HTTP proxy via fieldflow serve-http --reload and switch to the MCP bridge with fieldflow-mcp --transport stdio. Run the full suite through pytest, or narrow focus using pytest tests/test_app.py -k fields during debugging. The CI-equivalent local check set is ruff check fieldflow fieldflow_mcp tests, black --check fieldflow fieldflow_mcp tests, mypy fieldflow fieldflow_mcp, pytest, python -m build, and python -m pip check.
Coding Style & Naming Conventions
Python modules follow 4-space indentation, type hints, and descriptive snake_case names (tooling.py, StubAsyncClient). Run ruff check fieldflow fieldflow_mcp tests for linting and black --check fieldflow fieldflow_mcp tests for formatting validation; use black fieldflow fieldflow_mcp tests only when formatting is needed. Keep imports ordered (stdlib, third-party, local) and prefer explicit re-exports in fieldflow/__init__.py for public APIs. Use mypy fieldflow fieldflow_mcp when touching type-heavy parsing code.
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 · 23 lines · 760 tokens per session scan A 3527e5919ecf
fieldflow AGENTS.md is an instructions file published in the GitHub repository guillaumegay13/fieldflow (111 stars, last pushed 1mo ago), licensed MIT. It adds 760 tokens to every session, about $0.0038 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
Agent-Span AGENTS.md
AGENTS.md instructions for oxbshw/Agent-Span, covering agents.md, build & test, crate layout, adding a channel and adding an mcp tool.
relay-radar CLAUDE.md
Claude Code instructions for AetherCore-Dev/relay-radar, covering claude.md, build & development commands, install dependencies (yarn workspaces + turbo monorepo), build all packages and run all tests (107 tests across 6 suites).
openapi-sync-mcp CLAUDE.md
Claude Code instructions for jhlee0409/openapi-sync-mcp, covering claude instructions for openapi sync mcp, available tools, common workflows, 1. parse a spec and 2. find what uses a schema.
claude-tap AGENTS.md
Instructions for liaohch3/claude-tap, covering maintainer automation notes, agents 索引, documentation boundary, review guidelines and pre-commit hook.
skyvern CLAUDE.md
Claude Code instructions for Skyvern-AI/skyvern, covering claude.md, development commands, python backend commands, code quality & testing and frontend commands (in skyvern-frontend/).
opencodex AGENTS.md
AGENTS.md instructions for lidge-jun/opencodex, covering agents.md, what this project is, repository layout, optional subsystems stay off the core path and the devlog directory.