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-shipgit clone --depth 1 https://github.com/watt-mind/factoryWhat 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 | $0.00018 | $0.01221 |
| Opus 5 | $0.00009 | $0.00611 |
| Sonnet 5 | $0.00004 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
factory-ship 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship the current release: merge everything on the integration branch to the deploy branch. My invoking this command is the human master decision — the one call the autonomous loop never makes on its own. That means you carry it through to a verified deploy or a clear stop; don't hand it back to me half-done.
Interpret $ARGUMENTS as a repo name from config/repos.yaml (run from that repo's checkout); default is the repo you're standing in.
1. Resolve branches and preflight
- Branches come from
config/repos.yamlwhere the repo has an entry:base(integration, usuallydevelop) anddeploy_branch(usuallymaster). No entry or nodeploy_branch: use the repo's actual branches (develop→master/main); if base and deploy are the same branch, there is no release flow here — say so and stop. git fetch originfirst. Everything below readsorigin/<branch>, never a possibly-stale local ref.- Nothing to ship?
git log origin/master..origin/develop --oneline— empty means done, report and stop. - Is develop itself healthy? Latest CI run on the base branch must be green (
gh run list --branch develop --limit 1) and, where the repo has a smoke check (smoke_workflow/smoke_urlinrepos.yaml), the dev smoke must be green too. Shipping a red develop just promotes the breakage; fix or revert there first — that's a stop-and-notify, not something to push through. - Anything mid-flight? Open PRs targeting develop are fine — they ride the next release. But if a merge landed on develop in the last few minutes and its CI hasn't finished, wait for that run rather than shipping an unverified tip.
2. Open the release PR
- Reuse an existing open develop → master PR if one exists (
gh pr list --base master --head develop) — don't stack a second. - Otherwise create it. Title:
release: develop → master (<date>). Body: the commit list since last release (git log origin/master..origin/develop --oneline --no-merges) with Linear ticket IDs pulled out into their own line each, so the Linear integration links every shipped ticket. Do not putFixes <ID>in the body — these tickets are alreadyDone; a release PR references, it doesn't close.
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.
- 2d ago First seen · 50 lines · 18 tokens per session scan A b3c96ecec4b8
factory-ship is a command published in the GitHub repository watt-mind/factory (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,221 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.
app-ship
Ship a release — runs security review, then release-manager, gating on QA sign-off and clean bug board.
quick
Ship one tiny, already-decided low-risk change to dev within an hour — implementation, CI, merge, deploy and read-back.
release
Cut a release — bump all workspace versions in sync, generate/update CHANGELOG.md from Conventional Commits, commit and tag (push gated on confirmation).
commit-all
Stage and commit all current changes with a single message. Auto Git Push will pick up and push to origin within 30s.
app-learn
Mine a shipped app's conventions into the living House Knowledge Base — adds net-new learnings to knowledge/.md, harvests its failures into knowledge/failure-corpus.md, and flags conflicts for human decision.