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/watt-mind/factory/factory-mergegit clone --depth 1 https://github.com/watt-mind/factoryWrote 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/watt-mind/factory/factory-merge)<a href="https://agentmods.dev/commands/watt-mind/factory/factory-merge"><img src="https://agentmods.dev/badge/commands/watt-mind/factory/factory-merge.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.03987 |
| Opus 5 | $0.00007 | $0.01994 |
| Sonnet 5 | $0.00003 | $0.00797 |
| Haiku 4.5 | $0.00001 | $0.00399 |
Grade A, and why
factory-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 4d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review and land the open PRs for this repository. My invoking this command is the human merge decision for routine changes — but the review must be real, and sensitive changes still come back to me.
Interpret $ARGUMENTS as specific PR numbers or Linear issue IDs; default is every open PR in this repo (gh pr list, cross-checked against the team's In Review tickets so orphaned PRs and ticket-less PRs both surface).
Merge serialization & per-repo lock: Merges are strictly serialized per repository. Never run concurrent merge supervisors or merge processes against the same repository; a merge run holds exclusive lock over merge execution for that repo to prevent race conditions where one process merges PRs another process has escalated or modified.
--include-escalated is a one-off override used only by the foreground TUI's explicitly confirmed merge all action. It means the human has decided that existing escalated labels are not a hold for this run: include those PRs in the review and merge them when they otherwise meet the normal MERGE bar. Do not treat it as permission to merge with red CI, unresolved conflicts, a failing base/smoke check, or a blocking review finding. Do not apply this override merely because an escalated PR is visible; it must be present in $ARGUMENTS.
Per PR, in this order
1. Review first — always, even when CI is green
Start from the ticket's ## Handoff comment — dispatch posts one per PR (PR link, verification result, UX critique verdict, files vs Owned Paths, risks). It tells you where to concentrate: a stated risk gets read first, a FIX-FIRST resolved critique means re-checking those fixes, an exceptions line on Files means the Owned Paths check below already has a suspect. A missing or vague Handoff is a (minor) protocol finding to note — and a reason to trust the diff less, not to skip the review.
CI passing is not the bar. Prefer spawning the factory-merge-reviewer agent for this step — one per PR, with the ticket, Handoff comment, Owned Paths, and the repo's escalate_paths in its prompt — so the full diff never enters this session's context; act on its MERGE/FIX/ESCALATE report (it never merges or edits; you do). Where subagents are unavailable, read the full diff yourself. Either way the review covers:
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.
- 4d ago First seen · 118 lines · 14 tokens per session scan A 1f9e9578c220
factory-merge is a command published in the GitHub repository watt-mind/factory (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 3,987 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
release
Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.
check
Run the full local quality gate — TypeScript check, build, dependency audit (prod-only), skill registry validate. Fast pre-commit / pre-suggestdeploy sweep.
app-init
Start a new mobile app project — runs requirements intake, then CEO vision, then PRD + architecture in parallel.
app-status
Show the current state of the project — vision, sprint goal, board, blockers, daily report.
app-recover
Recover an interrupted run — reconcile the ledger, the board, the worktrees and the wave, then restart from a known state.
app-context
Create a deterministic provenance manifest before an agent starts work.