agentmods.dev

claude-code-workflow AGENTS.md

Repository instructions for coding agents working on a shared AI-work-system project. They describe how to preserve the project's structure, protect private information, and verify changes.

In plain words
What is it for?
Use them when editing the repository, writing documentation, creating examples, checking installed behavior, or preparing changes for release.
Why use it?
They prevent agents from turning a specific project into a generic template or exposing private data. They also clarify when documentation, plans, and public releases need special handling.

Instructions file for CodexOpenCode

711 4d ago A scan 227 tokens original MIT
View the source file runesleo/claude-code-workflow
Install

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.

agentmods
npx agentmods add instructions/runesleo/claude-code-workflow/agents-md
Clone the repo
git clone --depth 1 https://github.com/runesleo/claude-code-workflow

Made for: Codex, OpenCode.

Per session 227 This file is loaded in full into every session.
When invoked 227 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00227 $0.00227
Opus 5 $0.00113 $0.00113
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00023 $0.00023

Measured 2d ago against content hash bcc835d89d76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-workflow 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.

AGENTS.md · 13 lines

What it actually says

Repository Instructions

  • This repository publishes a sanitized map of Leo's current AI work system: a small shared Core, nine business lines, task continuity, background boundaries, and open-source branches.
  • Preserve the real topology and the reasons behind it. Do not flatten the project back into a generic workflow template.
  • Keep always-loaded instructions short. Put explanations in docs and load them only when relevant.
  • Never add absolute personal paths, live tasks, thread IDs, private state, credentials, accounts, positions, health records, customers, or production controls.
  • Public examples may preserve real contracts and business-line names, but their task content and timestamps must be explicitly synthetic.
  • Do not make plans, spawn agents, or add workflow artifacts for simple edits.
  • README.md and default docs are the Chinese source language. README.en.md and *.en.md files are compatibility mirrors.
  • Any behavioral claim must match the files users actually install.
  • Run ./scripts/verify.sh before declaring a change complete.
  • Pushes, tags, releases, and public posts require the maintainer's explicit approval.
Changes

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.

  1. 2d ago First seen · 13 lines · 227 tokens per session scan A bcc835d89d76

Subscribe to this mod's changes

claude-code-workflow AGENTS.md is an instructions file published in the GitHub repository runesleo/claude-code-workflow (711 stars, last pushed 4d ago), licensed MIT. It adds 227 tokens to every session, about $0.0011 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 2026-08-30.

agent-workflowai-agentsclaude-codecodexcursordeveloper-tools
Related

Other instructions, from other repositories

harness-workflow AGENTS.md

AGENTS.md instructions for YSAA1/harness-workflow, covering agents.md, 项目概览, 项目地图, 快速开始 and 项目铁律.

YSAA1/harness-workflow · 2,015 tokens

harness-workflow CLAUDE.md

Claude Code instructions for YSAA1/harness-workflow, a project described as: Context-aware agent workflow and project harness for Codex, Claude Code, and Cursor.

YSAA1/harness-workflow · 4 tokens

agentic-playwright selectors.instructions.md

Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.

idavidov13/agentic-playwright · 2,174 tokens

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens

llm-ide-rules pytest-integration-tests.instructions.md

Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.

iloveitaly/llm-ide-rules · 1,299 tokens

toki AGENTS.md

Instructions for choi138/toki, covering workspace rules, source of truth, toki workflow, required checks and global safety rules.

choi138/toki · 1,581 tokens