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-api-route-engineernpx skills add nonlinear-xyz/factory-kit --skill factory-api-route-engineergit clone --depth 1 https://github.com/nonlinear-xyz/factory-kitWrote 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/skills/nonlinear-xyz/factory-kit/factory-api-route-engineer)<a href="https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-api-route-engineer"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-api-route-engineer.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.01936 |
| Opus 5 | $0.00065 | $0.00968 |
| Sonnet 5 | $0.00026 | $0.00387 |
| Haiku 4.5 | $0.00013 | $0.00194 |
Grade A, and why
factory-api-route-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 5d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply the api-route-engineer specialist workflow. Build endpoints grounded in the factory's API conventions, not bespoke per-route handlers. Load the canonical factory-api and factory-auth skills through the host's skill capability when needed.
How to think (in order)
-
API style? Apply the decision matrix from
factory-api.md:- Server actions — default. One frontend consumer. Feature-folder colocation matters.
- tRPC — ≥3 entities with cross-feature queries. Multiple consumers. Typed RPC.
- REST / OpenAPI — only for external system callers.
If the project already commits to one, use it. Don't mix.
-
What's the surface?
- Mutation — create, update, delete, custom action
- Query — list (paginated), detail (by ID), search, aggregation
- Webhook — external system → your service
-
Auth tier?
- publicProcedure — only for genuinely public endpoints (signup, public docs)
- protectedProcedure — authed user, no org context
- orgProcedure — authed user + org context (default for app endpoints)
-
Input shape? Per-endpoint Zod schema. For paginated lists:
limit: number().int().min(1).max(100).default(50)offset: number().int().min(0).default(0)orderBy: enum([...]).default('createdAt')orderDir: enum(['asc','desc']).default('desc')- Plus per-feature filter object
-
Output shape? Three options:
- List:
{ items: T[], total?: number }— includetotalif pagination needs it - Detail:
T | null— return null on not-found, throwNotFoundErrorif the caller expected it - Mutation: the updated/created entity, or
ActionResult<T>for server actions
- List:
-
Multi-tenant filter? Every query / mutation in
orgProcedurefilters byctx.orgId. This is automatic enforcement, not "remember to add WHERE." -
Pagination shape?
- Offset — default for everything (admin tables, settings, normal CRUD)
- Cursor — only for real-time feeds, append-only logs, or pagination-stable-under-inserts requirements (chat messages, audit log)
-
Aggregations in list? If the list view needs counts (e.g. "customer with vehicle count"), use a subquery / leftJoin + groupBy rather than a per-row round-trip:
ctx.db.select({ ...getTableColumns(customers), vehicleCount: count(vehicles.id), }).from(customers).leftJoin(vehicles, ...).groupBy(customers.id); -
Error shape?
- Throw
AuthError,NotFoundError,ValidationErrorfromsrc/lib/errors.ts - For server actions, catch at the boundary and convert to
{ error: 'message' } - For tRPC, throw
TRPCError({ code, message })
- Throw
-
Audit log? Fire-and-forget at the mutation boundary. Never
awaitit on the critical path. Seefactory-security.md.
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.
- 5d ago First seen · 182 lines · 130 tokens per session scan A 7011bc0542b5
factory-api-route-engineer is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 1,936 once invoked, about $0.0006 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
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
skill-template
Generate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
check-environment
Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.
doc-writer
Documentation templates and standards: README structure, API reference format, changelog (Keep a Changelog), and comment guidelines. Use when creating or updating documentation. Loaded automatically by the doc-writer agent.