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 commands/zircote-plugins/github-agentic-workflows/aw-statusgit 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 | $0.00012 | $0.00493 |
| Opus 5 | $0.00006 | $0.00246 |
| Sonnet 5 | $0.00002 | $0.00099 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
aw-status 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.
What it actually says
/aw-status
Reads the persistent knowledge base and delivers a quick 300–400 word briefing on the current state of the gh-aw ecosystem. No web searches needed — this is a fast, offline status check.
Usage
/aw-status → Full briefing across all domains
/aw-status --domain gh-aw → Briefing focused on a specific domain
/aw-status --since 2026-04-01 → Only entries since the given date
Flags
--domain— Focus the briefing on a specific domain:gh-aw,actions,workspace,agent-mode,models,mcp-server,claude-code,community--since— Only include knowledge base entries from this date forward
Workflow
You are a briefing analyst. Deliver a concise status report from the knowledge base.
- Read the knowledge base at
skills/gh-aw-report/knowledge-base.md - Read
skills/gh-aw-report/references/gh-aw-architecture.mdfor architecture context - If
--domainis passed, filter entries to the specified domain - If
--sinceis passed, filter entries to those dated on or after the given date - Synthesize a 300–400 word briefing covering:
Briefing Format
## gh-aw Ecosystem Status — YYYY-MM-DD
### Current Versions
- gh-aw CLI: vX.Y.Z
- GitHub MCP Server: vX.Y.Z
- [other tracked versions]
### Active Deprecations
- [deprecation with timeline and migration path]
### Recent Changes (last 7 days)
- [notable changes from knowledge base]
### Recommended Actions
- [specific actions for workflow maintainers]
- If the knowledge base is empty or has no recent entries, report that and recommend running
/aw-reportto populate it.
Notes
- This command does NOT perform web searches — it reads only from the knowledge base
- For fresh intelligence, run
/aw-reportfirst - The knowledge base is updated by each
/aw-reportrun - Entries marked
[SUPERSEDED]are excluded from the briefing
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 · 61 lines · 12 tokens per session scan A dd20425a3944
aw-status is a command published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 493 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.
Other commands, from other repositories
discover
Run a full user research cycle — persona creation, empathy mapping, and journey mapping for a product or feature.
test-plan
Run the full usability study workflow — research questions, participant criteria, tasks, metrics, and facilitation guide.
execute
Run the autonomous implementation loop.
review-branch
Review an existing branch holistically before merging — blast radius, conventions, security, and spec compliance.
setup-tools
Detect missing CLI tools and install them to enhance Forge capabilities.
status
Show Forge progress and status.