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-cinpx 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.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 5.1 | $0.00110 | $0.03896 |
| Opus 5 | $0.00055 | $0.01948 |
| Sonnet 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 6d 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.
- 6d 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 1mo ago), licensed MIT. It adds 110 tokens to every session and 3,896 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
ci-cd
· Write/review CI/CD for GitHub Actions, GitLab, Forgejo/Gitea, Woodpecker. Triggers: 'ci/cd', 'pipeline', 'github actions', 'gitlab ci', 'runner', 'renovate', 'trivy'. Not for git workflows (use git).
cicd-supply-chain
Use when attacking or auditing a CI/CD pipeline or software supply chain — pwn requests, poisoned pipeline execution, compromised/mutable-tag actions, dependency confusion, registry worms, runner backdoors, OIDC trust abuse, SLSA/provenance.
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.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
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.
task-automation
Automate repetitive tasks and workflows using scripting, file watchers, scheduled jobs, CI triggers, and API polling to eliminate manual toil. Use when the user requests task automation or provides relevant inputs for this workflow.