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/zircote-plugins/github-agentic-workflows/claude-mdgit clone --depth 1 https://github.com/zircote-plugins/github-agentic-workflowsWhat 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 | $0.00831 | $0.00831 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
github-agentic-workflows CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — aw-author Plugin
Project
The aw-author Claude Code plugin (v1.3.2) at zircote/github-agentic-workflows. Provides skills, commands, and reference materials for GitHub Agentic Workflow (gh-aw) authoring, plus an autonomous daily intelligence pipeline.
Commands
/aw-author— Author, validate, improve, debug gh-aw workflow files/aw-daily [--dry-run] [--skip-research] [--skip-implementation] [--no-merge]— Autonomous daily pipeline: research → Discussion → gap analysis → implementation → PR todevelop/aw-merge [--dry-run] [--no-reset]— Weekly develop→main merge/aw-report [--deep] [--no-post] [--domains ...]— Intelligence sweep + Discussion posting/aw-status [--domain ...] [--since ...]— Quick KB briefing/aw-upgrade [--force] [--dry-run] [--no-merge] [--strict]— gh-aw extension upgrade cycle
Branching
main— stable productiondevelop— receives daily automated PRsdaily-intelligence-YYYY-MM-DD— ephemeral feature branches
Quality Gates
This project has no linter, type checker, or test suite. Quality gates are:
gh aw compile— all.mdworkflows in.github/workflows/must compile to.lock.ymlwith 0 errorsgh aw validate— all compiled workflows must validate with 0 errors- Cross-reference consistency — facts mentioned in one reference file must be consistent across all files that reference them
After editing any .github/workflows/*.md file, always recompile with gh aw compile and verify 0 errors.
Key Files
| Path | Role |
|---|---|
skills/aw-author/references/ |
9 canonical reference files — the core deliverable |
.claude/skills/aw-daily/SKILL.md |
9-phase autonomous pipeline |
.claude/skills/gh-aw-report/knowledge-base.md |
Persistent append-only KB |
.github/workflows/daily-intelligence.md |
Primary daily gh-aw workflow |
.github/workflows/weekly-develop-merge.md |
Weekly merge gh-aw workflow |
.claude-plugin/plugin.json |
Plugin manifest |
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.
- yesterday First seen · 67 lines · 831 tokens per session scan A f2ff982b5b6b
github-agentic-workflows CLAUDE.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 831 tokens to every session, about $0.0042 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
latchkey AGENTS.md
Instructions for imbue-ai/latchkey: For information about the high-level goal and motivations, see README.md.
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+).
get-fable AGENTS.md
Instructions for imMamdouhaboammar/get-fable, covering get-fable repository instructions, purpose, working contract, canonical lifecycle packs and runtime semantics.
atlas CLAUDE.md
Instructions for atlas-php/atlas: BEFORE ANY TASK: Read and follow AGENTS.md completely.
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 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|…