agentmods.dev

github-agentic-workflows AGENTS.md

Project instructions for the aw-author plugin, a Claude Code extension for creating GitHub Agentic Workflow files. They describe the repository, important directories, branching and agent rules.

In plain words
What is it for?
Use them when working on the aw-author plugin, its skills, GitHub Agentic Workflow references or automated workflows.
Why use it?
They give contributors the context and constraints needed to update the plugin and its reference materials consistently.

Instructions file for CodexOpenCode

2 1mo ago A scan 880 tokens original MIT
View the source file zircote-plugins/github-agentic-workflows
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/zircote-plugins/github-agentic-workflows/agents-md
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/github-agentic-workflows

Made for: Codex, OpenCode.

Per session 880 This file is loaded in full into every session.
When invoked 880 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 $0.00880 $0.00880
Opus 5 $0.00440 $0.00440
Sonnet 5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured yesterday against content hash fa92c7b96ca9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-agentic-workflows 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 yesterday.

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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions — aw-author Plugin

This file is read by all agentic runtimes (GitHub Copilot, Claude Code, Codex, and gh-aw workflows) when operating in this repository.

What This Repository Is

The aw-author plugin (v1.3.0) for Claude Code. It provides skills, commands, and reference materials for authoring GitHub Agentic Workflow (gh-aw) markdown files, plus an autonomous daily pipeline that keeps the reference materials current.

Repository: zircote/github-agentic-workflows Owner: Robert Allen (zircote)

Key Directories

  • skills/aw-author/references/ — 9 canonical reference files (frontmatter schema, safe-outputs, tools, gotchas, patterns, examples, validation, body guide, URLs). These are the primary deliverable of this project.
  • skills/aw-daily/ — Autonomous daily pipeline skill that researches the gh-aw ecosystem, identifies gaps in reference files, and creates PRs to fix them.
  • skills/gh-aw-report/ — Intelligence reporting skill with knowledge base and search queries.
  • .github/workflows/ — Two gh-aw workflows: daily-intelligence.md (daily research + updates) and weekly-develop-merge.md (weekly develop→main merge).
  • outputs/gh-aw-reports/ — Dated intelligence reports.

Branching

  • main — stable
  • develop — receives daily automated PRs from the intelligence pipeline
  • Feature branches: daily-intelligence-YYYY-MM-DD (ephemeral, deleted after merge)

Rules for All Agents

  1. Never edit .lock.yml files. They are compiled output from gh aw compile.
  2. Reference files are large (200–2100 lines). Use section headers as anchors for edits, not line numbers.
  3. Knowledge base (skills/gh-aw-report/knowledge-base.md) is append-only. Never delete entries. Mark outdated facts with [SUPERSEDED by YYYY-MM-DD].
  4. All add-comment safe-outputs must include discussions: false. This is a known gh-aw gotcha that causes HTTP 422 errors.
  5. The plugins: frontmatter field is deprecated. Use dependencies: instead. Run gh aw fix --write to migrate.
  6. Discussion posts go to the "Project News" category (ID: DIC_kwDORSXBr84C61Lr).
  7. The daily pipeline is idempotent. It checks for existing Discussions, PRs, and issues before creating new ones. Re-running on the same day is safe.
  8. When editing reference files, verify the change compiles. Run gh aw compile after modifying any .md file in .github/workflows/.
  9. PRs are created as drafts. Open with --draft or draft: true in safe-outputs, then mark ready with gh pr ready after all changes are pushed and verified.

Read the full file on GitHub · 58 lines

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. yesterday First seen · 58 lines · 880 tokens per session scan A fa92c7b96ca9

Subscribe to this mod's changes

github-agentic-workflows AGENTS.md is an instructions file published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 880 tokens to every session, about $0.0044 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.

Productivityagentic-aiai-toolsclaude-codeclaude-code-plugindeveloper-toolsgithub-actions
Related

Other instructions, from other repositories

latchkey AGENTS.md

Instructions for imbue-ai/latchkey: For information about the high-level goal and motivations, see README.md.

imbue-ai/latchkey · 164 tokens

cortex AGENTS.md

Instructions for CortexPrism/cortex, covering cortexprism — ai agent operating system, project identity, tech stack, build & ci commands and package structure (v0.48.6+).

CortexPrism/cortex · 3,181 tokens

get-fable AGENTS.md

Instructions for imMamdouhaboammar/get-fable, covering get-fable repository instructions, purpose, working contract, canonical lifecycle packs and runtime semantics.

imMamdouhaboammar/get-fable · 733 tokens

atlas CLAUDE.md

Instructions for atlas-php/atlas: BEFORE ANY TASK: Read and follow AGENTS.md completely.

atlas-php/atlas · 27 tokens

lihongwei-cn CLAUDE.md

Instructions for LiHongwei-cn/lihongwei-cn, covering claude.md — claude code 项目记忆, 用户身份, 回复风格（红线）, 网站 and 技术栈.

LiHongwei-cn/lihongwei-cn · 2,364 tokens

lihongwei-cn copilot-instructions.md

Instructions for LiHongwei-cn/lihongwei-cn: 1|# Universal Agent Spec — 通用规范核心 2| 3|> 本文件是所有 AI Agent 共享的行为规范。 4|> 各 Agent 适配文件（agents/ 目录）在部署时会把本文件内容与 Agent 专属配置合并。 5|> 修改本文件 = 修改所有 Agent 的行为。 6| 7|## 语言规则 8| 9|始终使用中文（简体中文）回复。 10| 11|仅以下内容使用英文： 12|- 代码本身（变量名、函数名、类名、关键字） 13|- URL 链接、命令行指令、API Key 14|…

LiHongwei-cn/lihongwei-cn · 1,631 tokens