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/genai-jerry/claude-software-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/genai-jerry/claude-software-factory/release)<a href="https://agentmods.dev/commands/genai-jerry/claude-software-factory/release"><img src="https://agentmods.dev/badge/commands/genai-jerry/claude-software-factory/release.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 5.1 | $0.00041 | $0.03875 |
| Opus 5 | $0.00020 | $0.01937 |
| Sonnet 5 | $0.00008 | $0.00775 |
| Haiku 4.5 | $0.00004 | $0.00387 |
Grade A, and why
release 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 3d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Release Manager of the Software Factory (see FACTORY.md).
Input: an issue number: $ARGUMENTS — which may be either:
- a task sub-issue at
factory:ready-to-ship(this is what thefactory:ready-to-shiphand-off notice and the Console's Start the Release Manager button pass, and what an expedited epic's chain dispatches). Read itstask(<epic>)title for the epic number — and itsPart of <owner>/<repo>#<n>marker for the epic's repo when it is elsewhere (§7) — and work the epic from there; or - the epic itself, normally at
factory:epic-readyafter a human opened gate GS.
Either way, resolve the epic first and read its state label: which phase you are in is a property of the epic, never of the task you were handed.
Step 0 — load the repo profiles
For each repo the epic touched, read .factory/profile.json — specifically
branches, estate_role, and the deploy block (health_checks, notes).
estate_role tells you where that repo sits in the dependency chain;
deploy.notes names the failure modes that must halt the train.
Step 0a — resolve each repo's integration and epic branches
Read .github/factory-branches.json in each repo — the org's branch policy
(FACTORY.md §6a/§6b). A missing file means {"staging": "staging", "required": true, "auto_create": true, "epics": false}; a missing epics
key means false.
- The integration branch's name is that repo's profile
branches.stagingwhen it is a non-null string, else the policy'sstaging. - The step is required unless the policy sets
required: false. - Required, and the branch does not exist on the remote: cut it from
branches.defaultwhen the policy'sauto_createis notfalse(git push origin origin/<default>:refs/heads/<integration>), and say so in your integration report. Ifauto_createisfalse, stop for that repo: comment on the epic naming the branch that has to exist, applyfactory:blocked, and do not merge anything there. required: falseand the repo has no integration branch: that repo has no phase 1b. Its task PRs are based on the default branch already, so skip to phase 2 and list those PRs themselves as the merge list. Say in the report that this repo ships without a staging proof, and why. Gate GS still applies: the epic reachesfactory:epic-readyand waits for approval before you list anything for a human to merge.- Epic branch (§6b): with
epics: trueand the epic's change folder merged ontofactory/epic-<epic-issue>(same name in every affected repo), that is the epic's assembly branch — phase 1 targets it. A pre-flip epic whose documents merged to the default branch has no epic branch: it has nothing to assemble onto, so its phase 1 only verifies, and phase 1b merges its task PRs onto the integration branch once gate GS is open.
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.
- 3d ago Changed · +108 lines · +3 tokens per session 70b52448cee2
- 7d ago First seen · 151 lines · 38 tokens per session scan A 8ecd1a77b6d3
release is a command published in the GitHub repository genai-jerry/claude-software-factory (2 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 3,875 once invoked, about $0.0002 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
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
ship
Ship is the operational release-prep flow for a connected project repo.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.
release
Standalone SDK release command for the BUILD repo. Not a workspace phase — runs independently after any number of implement/redteam cycles. Handles PyPI publishing, documentation deployment, and CI management for the kailash Python SDK and its framework packages.
create-pr
Push the current branch and open a pull request into main with a structured description derived from the branch's commits and issue references.