Borrowing it
Nothing to install: this file belongs to real-limitless/ansible-flow-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/real-limitless/ansible-flow-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/real-limitless/ansible-flow-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/real-limitless/ansible-flow-mcp/agents-md)<a href="https://agentmods.dev/instructions/real-limitless/ansible-flow-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/real-limitless/ansible-flow-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/real-limitless/ansible-flow-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/real-limitless/ansible-flow-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 | $0.04353 | $0.04353 |
| Opus 5 | $0.02176 | $0.02176 |
| Sonnet 5 | $0.00871 | $0.00871 |
| Haiku 4.5 | $0.00435 | $0.00435 |
Grade A, and why
ansible-flow-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 8d 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ansible-flow-mcp
Guidance for AI coding agents working in this repository.
What this is
ansible-flow-mcp is an MCP server that exposes Ansible to AI agents, plus an optional SSH hub/spoke multi-host fabric:
| Layer | Purpose |
|---|---|
| Core MCP | search_modules → get_module_schema → run_module / run_playbook (check-first) |
| Hub/spoke (issue #2) | Agent attaches to hub only; spokes enroll with join tokens; hub→spoke is SSH only |
| Operator TUI | Curses UI on hub: servers/groups CRUD, invite tokens, launch OpenCode |
Compose lab (lab/) |
Full hub + 3 spokes, smoke scripts, OpenCode bridge from host |
Not affiliated with Red Hat/Ansible beyond the public CLI. Dual-tracked with OpenFlow gallery concepts.
Product docs: README.md, docs/QUICKSTART.md, docs/HUB.md, docs/SECURITY.md, lab/README.md.
Layout
src/ansible_flow_mcp/
cli.py # entry: hub|spoke|tui|write-opencode-config|…
server.py # FastMCP tools; hub tools registered in hub mode
runner.py # ansible / ansible-playbook; hub inventory gates
catalog.py # gallery.json + catalog/schemas/*.json
policy.py # Role hub|spoke|legacy; enrolled hosts + groups
security.py # allowlist, redaction
ssh.py # spoke_call (ForceCommand simple-exec over SSH)
tui.py # operator TUI + write_opencode_hub_config
paths.py # ANSIBLE_FLOW_HUB_DIR / SPOKE_DIR defaults
hub/
state.py # hub init, keys, signing, audit.jsonl
tokens.py # issue/verify join tokens (HMAC, jti replay)
inventory.py # inventory.yml, spokes, custom groups
enroll.py # accept_join, revoke, update_node, group ops
spoke/
join.py # spoke join ceremony
session.py # ForceCommand: simple-exec or MCP stdio
catalog/ # MUST ship in wheel/image (do not dockerignore schemas/)
collections-allowlist.yml
gallery.json # ~25k modules
schemas/*.json # arg schemas for get_module_schema
docs/
HUB.md SECURITY.md campaign/ images/
site/ # marketing site (GitHub Pages) + Schema Lab
index|why|how|fabric|security|start.html
assets/ # Copper Busbar CSS + lab.js gallery/schema UI
examples/
cursor-mcp.json claude-desktop.json
opencode-hub.jsonc # in-process hub MCP for OpenCode
sshd/ hub/ # drop-ins + systemd examples
lab/ # integration lab (compose), NOT pytest
docker-compose.yml
docker-compose.windows.yml # opt-in dockur Windows (WinRM targets)
windows/ # oem WinRM scripts; storage gitignored
images/ # Dockerfile.hub|spoke, entrypoints, lab-opencode
scripts/ # demo, enroll, smoke, *-windows, tui, …
README.md
tests/ # unit tests (pytest)
test_runner.py test_catalog.py
test_hub_spoke.py test_hub_groups.py
scripts/ # generate_catalog.py, factory/ (Galaxy scrape)
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.
- 8d ago First seen · 377 lines · 4,353 tokens per session scan A 31237b7cc68b
ansible-flow-mcp AGENTS.md is an instructions file published in the GitHub repository real-limitless/ansible-flow-mcp (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 4,353 tokens to every session, about $0.0218 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.