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/copilot-instructionsgit 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 | $0.01587 | $0.01587 |
| Opus 5 | $0.00794 | $0.00794 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
github-agentic-workflows copilot-instructions.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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions — aw-author Plugin
Project Identity
This is the aw-author Claude Code plugin (v1.3.0) for authoring, validating, and maintaining GitHub Agentic Workflow (gh-aw) markdown files. The repository lives at zircote/github-agentic-workflows.
gh-aw workflows are markdown files with YAML frontmatter in .github/workflows/, compiled to .lock.yml via gh aw compile. This plugin provides the reference materials, skills, and automated pipelines that keep those workflows correct and current.
Repository Structure
commands/ Slash command entry points (/aw-author, /aw-daily, /aw-merge, /aw-report, /aw-status, /aw-upgrade)
skills/
aw-author/ Authoring skill + 9 reference files (the canonical gh-aw spec subset)
aw-daily/ Autonomous daily pipeline skill + gap analysis references
gh-aw-report/ Intelligence reporting skill + knowledge base + search queries
agents/
aw-analyst.md Deep analysis agent for workflow review
.github/workflows/
daily-intelligence.md Daily autonomous pipeline (gh-aw, fuzzy schedule)
daily-intelligence.lock.yml Compiled workflow (DO NOT EDIT)
weekly-develop-merge.md Weekly develop→main merge (gh-aw, fuzzy schedule)
weekly-develop-merge.lock.yml Compiled workflow (DO NOT EDIT)
outputs/gh-aw-reports/ Dated intelligence reports
Branching Strategy
main— stable, production branchdevelop— daily automated updates land here via PRdaily-intelligence-YYYY-MM-DD— ephemeral feature branches created by/aw-daily, deleted after merge todevelop- Weekly:
developmerges tomainvia/aw-merge(squash merge, then develop resets to main)
Daily Pipeline (.github/workflows/daily-intelligence.md)
This workflow runs daily around 07:00 (fuzzy schedule) and executes:
- Research — web fetch + GitHub API queries on 5 tracked repos (
github/gh-aw,github/github-mcp-server,github/copilot-cli,githubnext/agentics,zircote/github-agentic-workflows) - Knowledge base update — append stable facts to
skills/gh-aw-report/knowledge-base.md - Discussion posting — post report to Discussions in the "Project News" category
- Gap analysis — compare findings against 11 reference files in
skills/aw-author/references/andskills/gh-aw-report/references/ - Issue creation — file issues for identified gaps (max 5 per run, dedup by
[aw-daily]prefix) - Implementation — edit reference files on a branch from
develop - PR creation — PR to
developwithCloses #NNNlinks - Summary — report what changed
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 · 112 lines · 1,587 tokens per session scan A 925e7bdeaa76
github-agentic-workflows copilot-instructions.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 1,587 tokens to every session, about $0.0079 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|…