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.
git 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/commands/zircote-plugins/github-agentic-workflows/aw-upgrade)<a href="https://agentmods.dev/commands/zircote-plugins/github-agentic-workflows/aw-upgrade"><img src="https://agentmods.dev/badge/commands/zircote-plugins/github-agentic-workflows/aw-upgrade/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/commands/zircote-plugins/github-agentic-workflows/aw-upgrade"><img src="https://agentmods.dev/badge/commands/zircote-plugins/github-agentic-workflows/aw-upgrade.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 | $0.00018 | $0.02704 |
| Opus 5.5 | $0.00007 | $0.01082 |
| Sonnet 5.5 | $0.00004 | $0.00541 |
| Haiku 4.5 | $0.00002 | $0.00270 |
Grade A, and why
aw-upgrade scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aw-upgrade
End-to-end gh-aw upgrade, recompile, validate, and PR cycle. Designed for idempotent, unattended execution across many repos.
Usage
/aw-upgrade → Full upgrade cycle: upgrade extension → upgrade repo → validate → PR → merge
/aw-upgrade --force → Run even if gh-aw extension is already on latest version
/aw-upgrade --dry-run → Show what would change without committing or creating a PR
/aw-upgrade --no-merge → Create PR but do not auto-merge
/aw-upgrade --strict → Enforce strict mode validation for all workflows
Workflow
You are an operations automation agent performing an unattended gh-aw upgrade cycle. Execute the phases below in order. If any phase fails, stop immediately, report which phase failed and why, and do not proceed to subsequent phases.
Do not prompt the user for input at any point. This command is designed for bulk execution ($GPM_PROVISION_BULK=true).
Parse the argument string for flags: --force, --dry-run, --no-merge, --strict. Unknown flags should be rejected with an error message.
Phase 1: Pre-flight checks
- Verify
ghCLI is available:gh --version - Verify
gh awextension is installed:gh aw version- If not installed, install it:
gh extension install github/gh-aw - After install, capture version:
gh aw version
- If not installed, install it:
- Verify the current directory is a git repository with
.github/workflows/containing at least one.mdfile - Verify working tree is clean:
git status --porcelainmust be empty- If not clean, abort with error: "Working tree is dirty. Commit or stash changes before running /aw-upgrade."
- Capture the current branch name for later restoration
Report: current gh-aw version, repo name, number of .md workflow files found.
Phase 2: Upgrade gh-aw extension
- Record the before version:
gh aw version - Run:
gh extension upgrade github/gh-aw --force - Record the after version:
gh aw version - Compare versions:
- If versions are identical and
--forcewas NOT passed: report "gh-aw is already on latest version (vX.Y.Z). No upgrade needed." and exit successfully (skip all remaining phases). - If versions are identical and
--forceWAS passed: continue to Phase 3 with note "Forced recompile on same version." - If versions differ: report "Upgraded gh-aw from vX.Y.Z to vA.B.C" and continue.
- If versions are identical and
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 · 301 lines · 18 tokens per session scan A efeab8612a7b
aw-upgrade is a command published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 2,704 once invoked, about $0.0001 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 commands, from other repositories
ia-document-release
Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.
ia-changelog
Create engaging changelogs for recent merges to main branch.
release
Bump version, commit, push, mirror to ai-skills, and update local plugin.
release
Generate changelog, bump version, and create git tag.
repo-sprint
Collection health triage and work-session kickoff (dirty, unpushed, active, release candidates, audit gaps, stale, unpublished).
repo-week
Weekly activity summary across the repo collection (commits, releases, top churn) via repoindex digest.