gh-aw-report

A research and reporting skill for the GitHub Agentic Workflows ecosystem, including gh-aw, GitHub Actions, Copilot, models, MCP servers, and related community work. It searches multiple targeted sources, combines the findings, and updates a saved knowledge base.

In plain words
What is it for?
Use it for recurring ecosystem research, trend monitoring, and maintaining a shared reference of findings. It covers the full landscape or selected areas.
Why use it?
It turns scattered online updates into one dated report and preserves findings for later briefings. It can also publish the report to GitHub Discussions.

Skill for Claude CodeCodex

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 skills/zircote-plugins/github-agentic-workflows/gh-aw-report
Any agent
npx skills add zircote-plugins/github-agentic-workflows --skill gh-aw-report
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/github-agentic-workflows

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,708 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00079 $0.01708
Opus 5 $0.00039 $0.00854
Sonnet 5 $0.00016 $0.00342
Haiku 4.5 $0.00008 $0.00171

Measured 2d ago against content hash 217791e259fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/skills/gh-aw-report/SKILL.md · 192 lines

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

  1. GitHub Agentic Workflowsgithub/gh-aw, gh aw CLI
  2. GitHub Actions AI Features — AI-powered Actions, deprecations
  3. GitHub Copilot Workspace — browser-based agentic coding
  4. GitHub Copilot Agent Mode — IDE and CLI agentic coding
  5. GitHub Models API — model marketplace and API
  6. GitHub MCP Servergithub/github-mcp-server
  7. Claude Code × GitHub — Claude Code integrations
  8. Agentic CI/CD Community — patterns, tools, ecosystem

Execution Flow

Phase 1: Load Context

  1. Read the knowledge base at .claude/skills/gh-aw-report/knowledge-base.md to understand the current state of knowledge
  2. Read .claude/skills/gh-aw-report/references/gh-aw-architecture.md for stable architecture facts
  3. Read .claude/skills/gh-aw-report/references/search-queries.md for the query library
  4. 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:

  1. Run the web search
  2. Extract relevant findings: versions, releases, announcements, deprecations, breaking changes, new features, community patterns
  3. Discard noise (old results, unrelated matches, marketing fluff)
  4. 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 -->

Read the full file on GitHub · 192 lines

Files

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.

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 · 192 lines · 79 tokens per session scan A 217791e259fe

Subscribe to this mod's changes

gh-aw-report is a skill published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,708 once invoked, about $0.0004 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.