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/corteshvictor/vichu-flow/agents-mdgit clone --depth 1 https://github.com/corteshvictor/vichu-flowWrote 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/corteshvictor/vichu-flow/agents-md)<a href="https://agentmods.dev/instructions/corteshvictor/vichu-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/corteshvictor/vichu-flow/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 5.1 | $0.01005 | $0.01005 |
| Opus 5 | $0.00502 | $0.00502 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
vichu-flow 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 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.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Instructions for AI coding agents working in this repository. CLAUDE.md is a
symlink to this file (so both Claude- and AGENTS-aware tools read the same one).
Project overview
VichuFlow is an open-source, cross-platform Go runtime that runs workflows as
persistent state machines over any repository. It coordinates external coding
agents and decides stage transitions from evidence it verifies itself (running
the project's tests/lint/typecheck) — never from the agent's say-so. It ships a
single self-contained binary and is stack-agnostic (works on Node, Python,
Rust, Go, …); Go is only the language the binary is built in. Internal design
notes live in docs/internal/ (kept local, not committed).
Git
- NEVER commit, stage, push, create a branch, open a PR, or merge unless the
user explicitly asks for that exact action in the current turn. Treat git as
read-only by default. "Fix this" / "make the change" is permission to EDIT
FILES only — not to commit, push, or open/merge a PR. After editing, show the
diff and wait for the user to say what to do. Allowed without asking: read-only
inspection (
git status,git diff,git log). - NEVER merge anything to
main. Only the user decides what gets integrated, and only after they have reviewed it. Never integrate unreviewed changes. - NEVER add a
Co-Authored-Bytrailer (or any AI/assistant attribution) to commit messages. Commits are authored solely by the user. Hard rule. - Follow Conventional Commits v1.0.0:
<type>(<optional scope>): <description>. Types:feat,fix,perf,revert,refactor,docs,style,test,build,ci,chore. Use!for breaking changes. Scopes:engine,runtime,security,adapters,config,workflows,cli. - PRs are squash-merged; the PR title becomes the commit on
mainand must be a valid Conventional Commit (CIpr-title.ymlenforces it). - Branch naming:
<type>/<short-description>(e.g.feat/codex-adapter).
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 · 71 lines · 1,005 tokens per session scan A 95287ce90ed1
vichu-flow AGENTS.md is an instructions file published in the GitHub repository corteshvictor/vichu-flow (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,005 tokens to every session, about $0.0050 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
flow CLAUDE.md
Claude Code instructions for AixleHQ/flow, covering claude.md, documentation index, before pushing a branch or opening/updating a pr, docker is required and test parallelization.
atelier AGENTS.md
AGENTS.md instructions for duanecilliers/atelier, covering agents.md, what this is, commands, the seam contract - the #1 rule and architecture.
atelier CLAUDE.md
Claude Code instructions for duanecilliers/atelier: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
open-bridge AGENTS.md
AGENTS.md instructions for bks-lab/open-bridge, covering the bridge — agent instructions, required reading, session start detection (automatic), theme and agents.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.
agent-skills AGENTS.md
AGENTS.md instructions for simota/agent-skills, covering agents.md — claude-skills, repository purpose, language policy, repository structure and skill authoring conventions.