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-mergegit 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 | $0.00014 | $0.00670 |
| Opus 5 | $0.00007 | $0.00335 |
| Sonnet 5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
aw-merge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aw-merge
Weekly merge of develop into main. Creates a PR, waits for CI, squash merges, and resets develop to the new main HEAD.
Usage
/aw-merge → Full merge cycle
/aw-merge --dry-run → Show what would be merged, do not create PR
/aw-merge --no-reset → Merge but do not reset develop to main after
Flags
--dry-run— Show commits ondevelopahead ofmain, do not create PR or merge--no-reset— After merge, do not resetdeveloptomainHEAD (preserves divergent history)
Workflow
You are an autonomous operations agent performing the weekly develop-to-main merge.
Do not prompt the user for input at any point.
Phase 1: Check divergence
git fetch origin main develop
AHEAD=$(git rev-list --count origin/main..origin/develop)
If AHEAD is 0: report "develop is up to date with main. Nothing to merge." and exit.
If --dry-run: show git log --oneline origin/main..origin/develop and exit.
Phase 2: Create PR
gh pr create \
--draft \
--repo zircote/github-agentic-workflows \
--base main \
--head develop \
--title "chore: weekly develop merge $(date +%Y-%m-%d)" \
--body "## Summary
Weekly merge of \`develop\` into \`main\`.
**Commits:** $AHEAD commits since last merge.
\`\`\`
$(git log --oneline origin/main..origin/develop)
\`\`\`
---
_Automated by /aw-merge_"
Mark PR ready:
gh pr ready <PR_NUMBER>
Phase 3: CI and merge
- Wait for CI checks: poll
gh pr checksevery 15 seconds, max 5 minutes - If CI passes (or no checks configured): squash merge
gh pr merge --squash --auto --delete-branch=false
- If CI fails: leave PR open, report URL
Phase 4: Reset develop (unless --no-reset)
After successful merge, reset develop to match main:
git checkout develop
git reset --hard origin/main
git push --force-with-lease origin develop
git checkout main
git pull
Final Report
┌──────────────────────────────────────────┐
│ /aw-merge complete │
├──────────────────────────────────────────┤
│ Commits merged: N │
│ PR: URL │
│ Merged: yes/no │
│ develop reset: yes/no/skipped │
└──────────────────────────────────────────┘
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 · 100 lines · 14 tokens per session scan A 4348b626bc27
aw-merge is a command published in the GitHub repository zircote-plugins/github-agentic-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 670 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.