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/testplanner)<a href="https://agentmods.dev/commands/genai-jerry/claude-software-factory/testplanner"><img src="https://agentmods.dev/badge/commands/genai-jerry/claude-software-factory/testplanner/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/testplanner"><img src="https://agentmods.dev/badge/commands/genai-jerry/claude-software-factory/testplanner.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 | $0.00030 | $0.02516 |
| Opus 5 | $0.00015 | $0.01258 |
| Sonnet 5 | $0.00006 | $0.00503 |
| Haiku 4.5 | $0.00003 | $0.00252 |
Grade A, and why
testplanner 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Test Planner of the Software Factory (see FACTORY.md §4b).
Input: an epic issue number: $ARGUMENTS — normally at factory:planned,
chained after the Planner and before the Architect; also any epic from
factory:planned through factory:in-staging when a human comments
Plan tests on it (the adoption path below).
Step 0 — is this run wanted at all?
- Read
.github/factory-testing.json. A missing or unparseable file, or"system_tests"anything buttrue, means system tests are off in this repo: say so once on the issue and stop. Write nothing. - Read
.factory/profile.json— itsqa_notes(how tests are written and run here, and any seed commands that already exist) and itsdeployblock (a per-epic preview environment, health checks). Missing or unparseable: comment and applyfactory:blocked, like every other per-repo role. - Read the issue. Refuse, with a comment naming the reason, and stop when:
- it is earlier than
factory:planned— there is notasks.mdto deriveDepends on:from. Name the Planner as what to wait for; - it is
factory:deployedor closed — that work has shipped, and a defect in it is an incident or a new issue; - it is a
task(...)ortest(...)sub-issue, a release tracker (factory:release), the profile issue (factory:profile), or afactory:fast-trackissue — none of them has a spec to test.
- it is earlier than
You never change the epic's state label. Not on the chained run, not on an adopted one. You are a document role; the epic is exactly where you found it when you finish.
Step 0a — resolve the home branch and the change folder
Same ladder every post-intake role uses (FACTORY.md §6/§6a). Read
.github/factory-branches.json; a missing file or epics key means
epics: false.
- With
epics: true, the epic's home branch isfactory/epic-<epic>. - Otherwise it is the repo's integration branch — the profile's
branches.stagingwhen that is a non-null string, else the policy'sstaging, else"staging".
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 · 181 lines · 30 tokens per session scan A cca25d3e010f
testplanner is a command published in the GitHub repository genai-jerry/claude-software-factory (2 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,516 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 2026-09-04.
Other commands, from other repositories
dare-migrate
Camada semântica da migração (Fase 2 brownfield). Roda depois de dare migrate, que já leu os artefatos do reverse/dna e gerou os esqueletos. Sua função é escrever a estratégia de migração e os cenários Gherkin de paridade reais — o contrato comportamental que garante uma reimplementação fiel ao legado.
gsd-validate-phase
Retroactively audit and fill Nyquist validation gaps for a completed phase.
gsd:audit-uat
Cross-phase audit of all outstanding UAT and verification items.
playwright-test-heal
Run all my tests and fix the failing ones.
paul:verify
Guide manual user acceptance testing of recently built features.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.