A command that performs a broad online research sweep of the GitHub Agentic Workflows ecosystem and saves a dated Markdown report. It can also update the saved knowledge base and publish the report to GitHub Discussions.

Use it for regular gh-aw intelligence reports covering GitHub Actions, agent modes, models, MCP servers, Claude Code, and community activity.

It collects updates from several related areas in one run, so you do not have to research each area separately. Options let you run a deeper search, choose domains, or skip publishing.

aw-report — Command by zircote-plugins

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 commands/zircote-plugins/github-agentic-workflows/aw-report

Clone the repo

git clone --depth 1 https://github.com/zircote-plugins/github-agentic-workflows

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 526 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00526
Opus 5	$0.00006	$0.00263
Sonnet 5	$0.00003	$0.00105
Haiku 4.5	$0.00001	$0.00053

Measured yesterday against content hash 91d455548e16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.claude/commands/aw-report.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aw-report

Runs a full intelligence sweep across the GitHub Agentic Workflows ecosystem — 8+ web searches — and produces a dated Markdown report saved to outputs/gh-aw-reports/YYYY-MM-DD.md. Updates the persistent knowledge base and posts to GitHub Discussions.

Usage

/aw-report                     → Full sweep, all domains, post to Discussions
/aw-report --deep              → Extended sweep with deep-dive queries
/aw-report --no-post           → Generate report without posting to Discussions
/aw-report --domains gh-aw,mcp → Only sweep specified domains

Flags

--deep — Run additional deep-dive queries from the extended query library beyond the 8 primary searches
--no-post — Skip posting to GitHub Discussions (still saves report locally and updates knowledge base)
--domains — Comma-separated list of domains to sweep. Valid domains: gh-aw, actions, workspace, agent-mode, models, mcp-server, claude-code, community

Workflow

You are an intelligence analyst for the gh-aw ecosystem. Load the gh-aw-report skill to execute the full intelligence cycle:

Load context from the knowledge base and architecture reference
Execute the primary sweep (8 targeted web searches)
If --deep is passed, run additional deep-dive queries
If --domains is passed, filter to only the specified domains
Synthesize findings into a structured report
Save the report to outputs/gh-aw-reports/YYYY-MM-DD.md
Update the knowledge base with stable facts
Unless --no-post, post the report to GitHub Discussions in the project-news category at zircote/github-agentic-workflows
Print the final summary

Examples

/aw-report
# → Full sweep, saves report, updates KB, posts to Discussions

/aw-report --deep
# → Extended sweep with deep-dive queries on rich domains

/aw-report --no-post --domains gh-aw,mcp-server
# → Only sweep gh-aw core and MCP server, skip Discussions post

/aw-report --deep --domains claude-code
# → Deep dive on Claude Code × GitHub integrations only

Read the full file on GitHub · 54 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.

yesterday First seen · 54 lines · 13 tokens per session scan A 91d455548e16

Subscribe to this mod's changes

aw-report is a command published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 526 once invoked, about $0.0001 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.

Memory and context Productivity Research agentic-ai ai-tools claude-code claude-code-plugin developer-tools github-actions

aw-report

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/aw-report

Usage

Flags

Workflow

Examples

What this file has done since we first saw it

Other commands, from other repositories

discover

test-plan

execute

review-branch

setup-tools

status