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/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-ship)<a href="https://agentmods.dev/commands/watt-mind/factory/factory-ship"><img src="https://agentmods.dev/badge/commands/watt-mind/factory/factory-ship/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/watt-mind/factory/factory-ship"><img src="https://agentmods.dev/badge/commands/watt-mind/factory/factory-ship.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 | $0.02018 |
| Opus 5.5 | $0.00007 | $0.00807 |
| Sonnet 5.5 | $0.00004 | $0.00404 |
| Haiku 4.5 | $0.00002 | $0.00202 |
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 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 — 77 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. Pre-flight — run the command, don't re-derive it
Start here, always:
factory ship-preflight --repo <name> # read-only; exit 0 means shippable
It prints one PASS / FAIL / SKIP line per check and, on every FAIL, the exact command that fixes it. Do not proceed past a FAIL, and do not substitute your own reading of gh run list for it — this command exists because an agent spent ~2.5 h re-deriving these checks from ci.yml and memory (WM-1104). What it asserts, and why:
- The base tip is fully green for the exact SHA — every job of the CI workflow on the newest run for that commit, not "the latest run on the branch". A newer push cancels the previous run, so a stale run reads as red; a skipped job (
deploy-prodnever runs on develop) is not a failure; only jobs listed in the repo'sadvisory_jobsare allowed to be red. - Every runtime pin is fresh — for each role in the repo's
runtime_roles, the pinned source commit is an ancestor of the tip and nothing under that publisher's ownon.push.pathshas moved since. A stale pin means the release would ship source the runtime image does not contain. - No publisher is mid-flight and no bot pin PR is open — either means the pins are about to move under you.
- No
escalatedPR targets the base — that one is a human's decision, not a release's. - The promotion journal is clean (
ssh_probe) — a non-emptyactive/means a publish transaction, possibly another repo's, is still open; promoting over it strands the release.
Branches still come from config/repos.yaml: base (integration, usually develop) and deploy_branch (usually master). No entry or no deploy_branch: use the repo's actual branches; if base and deploy are the same branch, there is no release flow here — say so and stop. Nothing to ship? git log origin/master..origin/develop --oneline empty means done — report and stop. A repo with a dev smoke check (smoke_workflow/smoke_url) should have that green too. Shipping a red develop just promotes the breakage: fix or revert there first, which is a stop-and-notify, not something to push through.
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 Changed · +27 lines 8456a2dfc3f7
- 1mo 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 (19 stars, last pushed 17d ago), licensed Apache-2.0. It adds 18 tokens to every session and 2,018 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
release-swarm
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.
release-manager
Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages.
deploy
Run the complete ClawBridge release process. This is the ONLY way to deploy — follow every step.
release
Create a new release with version bump, changelog update, git tag, npm publish, and optional GitHub Release.
ci
Run CI validation, create PRs, and merge on green.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.