Borrowing it
Nothing to install: this file belongs to liuyingxuvka/FlowGuard. 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/liuyingxuvka/FlowGuard/main/AGENTS.mdgit clone --depth 1 https://github.com/liuyingxuvka/FlowGuardWrote 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/liuyingxuvka/flowguard/agents-md)<a href="https://agentmods.dev/instructions/liuyingxuvka/flowguard/agents-md"><img src="https://agentmods.dev/badge/instructions/liuyingxuvka/flowguard/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/liuyingxuvka/flowguard/agents-md"><img src="https://agentmods.dev/badge/instructions/liuyingxuvka/flowguard/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 | $0.00625 | $0.00625 |
| Opus 5.5 | $0.00250 | $0.00250 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
FlowGuard 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 2d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlowGuard repository rules
FlowGuard maintains one model tree of the project (map, executable models and tests bound to the code), with a current and a target model. This repository uses FlowGuard on itself.
Every task in this repository
python -m flowguard read- read the map first; open only the files of the components you touch.- Behaviour or structure change: target first (
target start,target add,target check, thentarget promote); code-only change: edit directly. Keep responsibilities single-owned; extend the existing owner instead of adding a second one. python -m flowguard change- fix every check error; run the tests and models it lists.- Update the description of every component listed as REVIEW, then
python -m flowguard map confirm <id>. - Before each push, run the affected checks selected above and report their results. For the final frozen source SHA, the complete
ci.ymlworkflow must pass: Ubuntu Python 3.11 runspython -m pytest -qandpython -m flowguard releaseonce; Ubuntu Python 3.13 and Windows Python 3.12 run the core path/packaging test files listed in ci.yml and the real skill copy/--check. Those two smoke environments do not claim complete cross-platform coverage. Publication waits for the entire workflow on the exact source SHA; do not repeat the full local suite solely to produce another checkpoint.
Layout
flowguard/engine, node kinds (validator.py,ui_flow.py), the test-tree shard tool;flowguard/map/map, target, discovery and proof layer..agents/skills/flowguard/the single public skill (SKILL.md, references)..flowguard/map.json,.flowguard/models/: FlowGuard's own map and models..flowguard/cache/is never committed.tests/unit tests;examples/runnable teaching models;docs/long-form notes.
Rules
- No generated check outputs, execution records or standalone hashes in git except the
fingerprintfields written byconfirm. - Do not add a second way to do something that already has an owner; extend the owner.
- When
map lintreports a real architecture problem you are not fixing now, record it inaccepted_debtswith a reason instead of hiding it. - Report exactly which commands you ran and their results; never mark unrun checks as passed.
- Installing the skill (
python scripts/install_skill.py --target <skills dir>), tagging and publishing are separate steps that need the maintainer's explicit request.
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.
- 2d ago Changed · -7 tokens per session eb65ef539096
- 6d ago Changed · +43 tokens per session 60441771c526
- 8d ago Changed · +3 lines · +43 tokens per session 733ec8f44076
- 12d ago Changed · +104 tokens per session 7569db295ee1
- 16d ago Changed · -72 lines · -830 tokens per session 8bc2d8f0e94f
- 22d ago Changed · +79 tokens per session ebbc390db6b1
- 1mo ago Changed · +4 lines · +26 tokens per session f3de6a97b1e4
- 1mo ago Changed · -56 lines · -1,820 tokens per session 364ed5e751a1
- 1mo ago Changed 90815ddffd08
- 1mo ago First seen · 156 lines · 2,987 tokens per session scan A 2c53a33ad897
FlowGuard AGENTS.md is an instructions file published in the GitHub repository liuyingxuvka/FlowGuard (2 stars, last pushed 2d ago), licensed MIT. It adds 625 tokens to every session, about $0.0025 per session on Opus 5.5. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.