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/nonlinear-xyz/factory-kit/factory-apinpx skills add nonlinear-xyz/factory-kit --skill factory-apigit clone --depth 1 https://github.com/nonlinear-xyz/factory-kitWhat 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 | $0.00095 | $0.03955 |
| Opus 5 | $0.00048 | $0.01978 |
| Sonnet 5 | $0.00019 | $0.00791 |
| Haiku 4.5 | $0.00010 | $0.00396 |
Grade A, and why
factory-api 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory api
Each section leads with Principle (one sentence, stack-agnostic), then Why (constraint → option → tradeoff), then Recipe (the Next.js / Drizzle / tRPC shape we use), and Failure mode when there's one to name. Sections that are pure style with no deeper truth are marked Recipe only. Editors: if the Principle could appear unchanged in Clean Code, sharpen the Why with a Factory-specific observation or drop the section to Recipe only — honesty over inflation.
API style — pick one
Principle. Pick one transport style per project; don't mix server actions and tRPC.
Why. Two transport styles in one codebase means two error-handling conventions, two cache-invalidation patterns, two surfaces to audit. The cost compounds linearly with every new endpoint; the cleanup is almost never worth the disruption. The decision is cheap at project start and expensive six months in.
Recipe.
| Style | Pick when |
|---|---|
| Server actions | Default. Feature-folder colocation matters. One frontend consumer. App-internal API only. Pairs with TanStack Query useMutation. |
| tRPC | ≥3 entities with cross-feature queries. Multiple frontend consumers. Need typed RPC across a real network boundary. |
| REST / OpenAPI | Only when an external system needs to call you. Don't use for internal app traffic. |
Failure mode. Encode imported tRPC at project start and built the rest in server actions; the unused tRPC surface created confusion at every call site for months before being deleted.
Server actions — canonical shape
Principle. Every mutation: parse input first, then wrap with org context, then fire-and-forget the audit log.
Why. Three contracts in tension. Validation is the boundary guarantee — past safeParse, downstream code assumes the shape. Org context is the tenant guarantee — without it, a cross-tenant write is one missing filter away. Audit is the reconstructability guarantee — but it's after-the-fact, so it never blocks the response. The order matters: validation can refuse; org context can refuse; audit can fail silently.
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 · 403 lines · 95 tokens per session scan A 9822a0fe7381
factory-api is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 29d ago), licensed MIT. It adds 95 tokens to every session and 3,955 once invoked, about $0.0005 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
databases
· Configure/tune/migrate PostgreSQL, MongoDB, MySQL/MariaDB, MSSQL. Triggers: 'database', 'postgres', 'mysql', 'mongodb', 'schema', 'migration', 'pgbouncer', 'EXPLAIN'. Not for HTTP APIs (use backend-api).
schema-evolve
This skill should be used when the user asks about 'schema drift', 'schema evolution', 'evolve schema', 'schema sync', 'sync schemas', 'update schema fields', 'schema field frequency', 'missing schema fields', 'unused schema fields', 'schema proposal', 'schema cardinality', 'check schema', 'schema audit', 'schema…
audit-data-integrity
Use when auditing and fixing end-to-end data integrity in a scope — invariant violations, partial or conflicting writes, unsafe migrations/backfills, duplicate or reordered effects, precision or time corruption, stale derived stores, broken retention/deletion, and unrecoverable drift. Triggers on "audit data…
lark-base
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、workflow、角色权限；遇到 Base/多维表格/bitable 或 /base/ 链接时使用。文件导入/导出转 lark-drive，认证/授权转 lark-shared。.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
postgres-database-migration
Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases. Trigger when user asks to: Test a schema migration before applying it to production Add, remove, or rename columns safely on a live table Change a column's data…