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 skills add nonlinear-xyz/factory-kit --skill factory-cigit 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-ci)<a href="https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-ci"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-ci/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/skills/nonlinear-xyz/factory-kit/factory-ci"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-ci.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 | $0.00110 | $0.03896 |
| Opus 5.5 | $0.00044 | $0.01558 |
| Sonnet 5.5 | $0.00022 | $0.00779 |
| Haiku 4.5 | $0.00011 | $0.00390 |
Grade A, and why
factory-ci 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 1mo 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory CI
Each section leads with Principle (one sentence, stack-agnostic), then Why (constraint → option → tradeoff), then Recipe (the GitHub Actions / branch protection / Claude reviewer shape we use), and Failure mode when there's one to name.
The kit is opinionated on the recipe layer (GitHub Actions + anthropics/claude-code-action). A reader on GitLab / Buildkite can read the principle and skip the recipe; the merge-gate, required-check, and automated-review principles are stack-agnostic.
One canonical workflow gates merge
Principle. A single .github/workflows/ci.yml is the merge gate; nothing else gates merge; branch protection's required-checks list matches that workflow's jobs 1:1.
Why. Multiple workflows that each "kind of" gate merge create ambiguity — when a PR is red, no one knows which job to look at, and a "flaky" job becomes optional in practice within a week. A single canonical file is the source of truth; the required-checks list is the contract with reviewers. The trade-off accepted: the single file gets longer than any individual concern's natural footprint; that's the cost of one place to look.
Recipe. ci.yml has exactly these jobs: typecheck, lint, test, build, claude-review. Each is a required check in branch protection. Deploy lives in deploy.yml (see factory-deployment.md) and is never a required check on PRs — deploy gates the next environment, not the merge.
# .github/workflows/ci.yml
name: ci
on:
pull_request:
types: [opened, synchronize, reopened]
push:
branches: [main]
jobs:
typecheck:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- uses: actions/setup-node@v4
with: { node-version: 20, cache: pnpm }
- run: pnpm install --frozen-lockfile
- run: pnpm typecheck
lint:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- uses: actions/setup-node@v4
with: { node-version: 20, cache: pnpm }
- run: pnpm install --frozen-lockfile
- run: pnpm lint
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: neondatabase/create-branch-action@v5
id: neon
with:
project_id: ${{ secrets.NEON_PROJECT_ID }}
parent: main
branch_name: pr-${{ github.event.pull_request.number }}
- uses: pnpm/action-setup@v4
- uses: actions/setup-node@v4
with: { node-version: 20, cache: pnpm }
- run: pnpm install --frozen-lockfile
- run: pnpm db:migrate
env:
DATABASE_URL: ${{ steps.neon.outputs.db_url }}
- run: pnpm test:coverage
env:
DATABASE_URL: ${{ steps.neon.outputs.db_url }}
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- uses: actions/setup-node@v4
with: { node-version: 20, cache: pnpm }
- run: pnpm install --frozen-lockfile
- run: pnpm build
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.
- 1mo ago First seen · 252 lines · 110 tokens per session scan A bf2890273f39
factory-ci is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 9d ago), licensed MIT. It adds 110 tokens to every session and 3,896 once invoked, about $0.0004 per session on Opus 5.5. 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
ln-63-deployment-engineer
Prepares delivery pipelines and remote infrastructure, then executes authorized rollouts; not standalone quality-gate setup or local container packaging.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
gemini-review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.
code-reviewer
Code review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.
operating-infra
Author, inspect, troubleshoot, review, and apply (after explicit confirmation) infrastructure across IaC, Kubernetes, cloud resources, containers, CI/CD, and Linux hosts. Use when changing Terraform/OpenTofu, Kubernetes, Helm, Kustomize, Dockerfiles, GitHub Actions workflow/job/permissions semantics, AWS, GCP, Cloud…