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-capturegit 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 | $0.00021 | $0.00970 |
| Opus 5 | $0.00010 | $0.00485 |
| Sonnet 5 | $0.00004 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
factory-capture 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn what just came up in this conversation into a Linear issue. This command only files — it never implements, and it never claims the ticket. If the finding should also be worked, that's a separate step (claim it yourself, or hand it to /factory-work).
1. Find what to file
$ARGUMENTS names the finding if given; otherwise scan the conversation so far for the thing worth tracking — a bug, a missing requirement, tech debt, a follow-up idea, an operational finding. If more than one distinct thing surfaced, ask which one, or file each separately — don't merge unrelated findings into one issue.
Confirm it clears the bar in docs/protocol.md §8 before filing anything: meaningful, trackable work (a code/config change, deployment, deliverable, or an investigation with an operational finding) — not an ordinary question, a read-only lookup with no actionable finding, or an inconsequential edit. If it doesn't clear the bar, say so and don't file.
2. Route it
Repo → team/project mapping, and the full ai:*/source:*/type:*/area:* label taxonomy, are in $FACTORY_ROOT/docs/protocol.md §1–3 — read it if this session hasn't already. A repo may carry its own issue-management guide; follow that inside that repo and do not import another team's labels into it.
If the current working directory matches a repo in config/repos.yaml, use its team/project. Otherwise infer team/project from what the conversation was actually about — ask if it's genuinely ambiguous rather than guessing.
Search for duplicates first (factory ticket, per docs/protocol.md §13) — don't file a second issue for something already tracked; comment on the existing one with the new evidence instead and report that back, not a new issue.
3. Label and specify
Every issue gets exactly one source:* label at creation. This came from a human talking in chat, so default to source:human — use source:agent only if the finding is something an agent noticed while doing other work and the human is just asking to have it recorded. Add the canonical type:* and area:* labels, and set priority from evidence in the conversation (severity, frequency, blast radius) — never left at default.
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 · 43 lines · 21 tokens per session scan A f67044989f33
factory-capture is a command published in the GitHub repository watt-mind/factory (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 21 tokens to every session and 970 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.
commit-all
Stage and commit all current changes with a single message. Auto Git Push will pick up and push to origin within 30s.
check
Run the full local quality gate — TypeScript check, build, dependency audit (prod-only), skill registry validate. Fast pre-commit / pre-suggestdeploy sweep.
app-init
Start a new mobile app project — runs requirements intake, then CEO vision, then PRD + architecture in parallel.
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.
app-status
Show the current state of the project — vision, sprint goal, board, blockers, daily report.