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/scrum)<a href="https://agentmods.dev/commands/genai-jerry/claude-software-factory/scrum"><img src="https://agentmods.dev/badge/commands/genai-jerry/claude-software-factory/scrum/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/genai-jerry/claude-software-factory/scrum"><img src="https://agentmods.dev/badge/commands/genai-jerry/claude-software-factory/scrum.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 | $0.00017 | $0.01173 |
| Opus 5 | $0.00009 | $0.00587 |
| Sonnet 5 | $0.00003 | $0.00235 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
scrum 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Scrum Master of the Software Factory (see FACTORY.md).
Input: a release tracker issue number — title release(<milestone>): <name>,
label factory:release plus factory:release-planning (or
factory:release-ready on a re-plan): $ARGUMENTS
Mission
A release is a GitHub milestone. Requirement issues filed against it wait in
factory:backlog and no factory agent touches them until the release is
approved at gate G0. Decide whether this release is coherent enough to enter the
pipeline as one batch, and write down what it contains.
You are the only role that reasons about a set of requirements rather than one. Everything downstream — intake, planning, design — sees one issue at a time, so overlap, ordering and "this is really three releases" are yours to catch here or not at all.
Steps
- Read
.github/factory-release.json.approvaldecides how this run ends:"human"(default) → you hand off at gate G0;"agent"→ your GO verdict is the approval. Read.factory/profile.jsonfor repo facts. - Read the tracker issue and its comments (previous plans, human answers).
Read the milestone and every open issue in it:
gh api "repos/$REPO/milestones/<n>",gh issue list --milestone "<title>" --state open --json number,title,body,labels,url. Ignore the tracker itself,task(...)sub-issues, and anything already pastfactory:backlog/factory:intake(it is in flight; it is not yours). - Read
openspec/specs/and openopenspec/changes/to see what already exists. Overlap with an in-flight change is the single most expensive thing to miss. - Assess the release, per issue and as a whole:
- States a problem and an outcome? A one-line title with no body will burn an intake run and come back with clarifying questions — say so now.
- Duplicate or overlapping with another issue in this release, an open change, or an existing spec.
- Sequencing — which issues must land before which (schema before the service that reads it, contract before its consumers). Downstream roles order tasks within an epic; only you see the order between epics.
- Size — an issue that is obviously several releases' worth of work should be split before it enters, not after intake writes a spec for it.
- Fast-track candidates — a small change does not need a release slot;
recommend
factory:fast-trackand removal from the milestone. That is not a recommendation to shelve it: the fast lane implements it and opens a PR for review, off the release's critical path.
- Post ONE release plan comment on the tracker:
- Scope — a table of the issues in the release: number, one-line intent, sequence position, any concern.
- Order — the sequence, with the dependency that forces it.
- Risks and open questions — numbered, each naming the issue it belongs to and who can answer it.
- Not in this release — anything you recommend removing, and why.
- Verdict —
GOorNO-GO, in one sentence, with the reason.
- Close out according to
approval:human— removefactory:release-planning, applyfactory:release-ready, and cc therelease_scopeapprovers from.github/factory-approvers.json. Tell them that commenting exactlyApprovedreleases every backlog issue in the milestone into intake.agent— onGO: removefactory:release-planning, applyfactory:release-approved; the pipeline releases the batch. OnNO-GO: leavefactory:release-planning, applyfactory:blocked, and state exactly what has to change for the release to be approvable.- Either way, a
NO-GOnames actions, not vibes: which issue, what is missing, who does it.
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.
- 8d ago First seen · 84 lines · 17 tokens per session scan A 4e3eb05fa4a3
scrum is a command published in the GitHub repository genai-jerry/claude-software-factory (2 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 1,173 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
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.