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 skills add zircote-plugins/github-agentic-workflows --skill gh-aw-reportgit clone --depth 1 https://github.com/zircote-plugins/github-agentic-workflowsWrote 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/skills/zircote-plugins/github-agentic-workflows/gh-aw-report)<a href="https://agentmods.dev/skills/zircote-plugins/github-agentic-workflows/gh-aw-report"><img src="https://agentmods.dev/badge/skills/zircote-plugins/github-agentic-workflows/gh-aw-report/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zircote-plugins/github-agentic-workflows/gh-aw-report"><img src="https://agentmods.dev/badge/skills/zircote-plugins/github-agentic-workflows/gh-aw-report.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.01708 |
| Opus 5.5 | $0.00032 | $0.00683 |
| Sonnet 5.5 | $0.00016 | $0.00342 |
| Haiku 4.5 | $0.00008 | $0.00171 |
Grade A, and why
gh-aw-report 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 1mo 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gh-aw Ecosystem Intelligence Report
You are an intelligence analyst for the GitHub Agentic Workflows (gh-aw) ecosystem. Your mission is to produce a comprehensive, dated intelligence report covering the full gh-aw landscape.
Covered Domains
- GitHub Agentic Workflows —
github/gh-aw,gh awCLI - GitHub Actions AI Features — AI-powered Actions, deprecations
- GitHub Copilot Workspace — browser-based agentic coding
- GitHub Copilot Agent Mode — IDE and CLI agentic coding
- GitHub Models API — model marketplace and API
- GitHub MCP Server —
github/github-mcp-server - Claude Code × GitHub — Claude Code integrations
- Agentic CI/CD Community — patterns, tools, ecosystem
Execution Flow
Phase 1: Load Context
- Read the knowledge base at
.claude/skills/gh-aw-report/knowledge-base.mdto understand the current state of knowledge - Read
.claude/skills/gh-aw-report/references/gh-aw-architecture.mdfor stable architecture facts - Read
.claude/skills/gh-aw-report/references/search-queries.mdfor the query library - Determine today's date with
date +%Y-%m-%d
Phase 2: Intelligence Sweep
Execute the 8 primary sweep queries from references/search-queries.md using WebSearch. For each query:
- Run the web search
- Extract relevant findings: versions, releases, announcements, deprecations, breaking changes, new features, community patterns
- Discard noise (old results, unrelated matches, marketing fluff)
- Note the source URL for each finding
If a domain yields particularly rich results, run additional deep-dive queries from the query library.
Phase 3: Synthesize Report
Produce a structured Markdown report with these sections:
# gh-aw Ecosystem Intelligence Report — YYYY-MM-DD
## Executive Summary
<!-- 3-5 bullet points: most important findings across all domains -->
## 1. gh-aw Core
<!-- Version updates, CLI changes, breaking changes, new features -->
## 2. GitHub Actions AI
<!-- Platform changes, new features, deprecations affecting agentic workflows -->
## 3. Copilot Workspace
<!-- New capabilities, changes, availability updates -->
## 4. Copilot Agent Mode
<!-- IDE/CLI agent updates, new tools, model changes -->
## 5. GitHub Models API
<!-- New models, API changes, deprecations -->
## 6. GitHub MCP Server
<!-- Releases, new tools, protocol changes -->
## 7. Claude Code × GitHub
<!-- Integration updates, new features, MCP improvements -->
## 8. Agentic CI/CD Community
<!-- New tools, patterns, blog posts, community developments -->
## Deprecation Watch
<!-- Active deprecations with timelines and migration guidance -->
## Recommended Actions
<!-- Specific actions for maintainers of gh-aw workflows -->
## Sources
<!-- Numbered list of all URLs referenced in the report -->
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 192 lines · 79 tokens per session scan A 217791e259fe
gh-aw-report is a skill published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 1,708 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
github-release-management
Use when cutting a GitHub release that needs progressive canary rollout (5%→25%→50%→100%) with automated health gates and auto-rollback on error-rate or latency regressions.
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
dependency-triage
Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
output-standards
Use this skill when defining or enforcing output formatting standards for agent responses in WrongStack. Triggers: user says "next steps format", "output standard", "response format", "final message format", "standardize next steps".
web-platform-baseline
Use this skill before asserting that a CSS, HTML or accessibility capability is available, unavailable, or the right tool — it carries dated, refreshable platform facts and refuses to let stale knowledge be stated as current. Triggers: user says "container query", "can I use", "browser support", "modern CSS", ":has"…