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 skills/squidbay/factory/engineernpx skills add squidbay/factory --skill engineergit clone --depth 1 https://github.com/squidbay/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 | $0.00083 | $0.00586 |
| Opus 5 | $0.00042 | $0.00293 |
| Sonnet 5 | $0.00017 | $0.00117 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
engineer 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.
What it actually says
Engineer boot — thin loader
Normally you never need this skill: the repo's own CLAUDE.md boots the Engineer automatically the moment the repo is attached to a Claude Code session. This skill is the fallback trigger for the same boot — if you're here because the auto-boot didn't fire, treat that as a flag worth mentioning to the human (RULE 11), then boot anyway.
This card is now named for the seat: engineer. Its parent folder still reads seats/worker/ — that one is an address, not a name, and the retired-folder sweep is a later step.
On invocation:
- Read
seats/worker/BOOT-PROMPT.mdin this repo, off livemain, in full. That file is the boot; this skill only points at it. - Follow it exactly: it will send you to
seats/_shared/BOOT-COMMON.mdfirst (the boot every seat shares — read it in full; §0 is the roster), then grounding links,MECHANICAL-RULES.md,seats/worker/OVERRIDES.md, and the top ofjournal.md, then the merged spec for your task — and confirm the boot per RULE 17. - Remember the write path before anything else: branch + PR only, never
main, never merge (RULE 14).
Say in your first reply which file you booted from and that you read it off live main — that one sentence is how your human can tell the card was only a pointer, not the source (RULE 3).
What this card is, and what it is not. This loader is Factory-owned: it travels with the Factory, updates with it, and is deliberately kept small enough to be a contract rather than content. The boot material it points at — BOOT-PROMPT.md, GROUNDING.md, OVERRIDES.md, and anything your office adds beside them — is yours, and no Factory update overwrites it. That split is declared in .github/template-manifest.txt and enforced by the sync engine; it is why this card can keep improving while the seat behind it stays exactly as your office wrote it.
If this skill and the repo's boot prompt ever disagree, the boot prompt wins — and say you noticed.
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 · 23 lines · 83 tokens per session scan A 8a02297f1a9f
engineer is a skill published in the GitHub repository squidbay/factory (5 stars, last pushed 11d ago), licensed MIT. It adds 83 tokens to every session and 586 once invoked, about $0.0004 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 skills, from other repositories
stage-plan
How to turn "here is my material + here's the video I want" into a single, inspectable plan that spans reference images, reference videos, deterministic editing, semantic editing, generation, and composition. The output is project/plan.json — a cross-modal Edit Decision List (EDL) — which the assembler walks.…
frontend-design
Use this as the design-lead layer for VideoStudio COMPOSE work. It shapes project/composition/composition-manifest.json::artdirection and the model-authored HTML/SVG motion graphics in index.html.
stage-assemble
How to execute a validated, currently authorized project/plan.json into one finished file. Start/resume with production.status; if planapprovalcurrent is false, pass the state to gate-control and stop instead of producing or opening child gates. Walk the signed EDL; do not re-plan. Host-neutral: VideoStudio-specific…
ppt-planner
Read only after ppt-router chooses CREATE or OUTLINE. Planning is the source of truth for construction, not optional prose around the deck.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.
design-system-importer
Use this when COMPOSE or an AUTO compose segment has any external reference media or style source: a reference image, reference video, DESIGN.md, brand guide, screenshot, existing website, design notes, or an explicit named visual direction.