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-commitsnpx skills add nonlinear-xyz/factory-kit --skill factory-commitsgit 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-commits)<a href="https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-commits"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-commits.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 | $0.00058 | $0.02108 |
| Opus 5 | $0.00029 | $0.01054 |
| Sonnet 5 | $0.00012 | $0.00422 |
| Haiku 4.5 | $0.00006 | $0.00211 |
Grade A, and why
factory-commits 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory commits
Each section leads with Principle (one sentence, stack-agnostic), then Why (constraint → option → tradeoff), then Recipe (the commitlint / Husky / opencommit shape we use), and Failure mode when there's one to name.
Tie every commit to a Linear issue
Principle. Every commit references a Linear issue ID in the subject or body; the commit hook enforces it.
Why. Code changes without ticket linkage are unsearchable history — six months later, "why did we change this?" has no answer that doesn't require a full archaeology session. Linear linkage makes the graph dense: ticket → PR → commit → context → decision. Each link is cheap up front; the lookup savings compound. Enforcement via commit-msg hook is the difference between "we should" and "we do."
Recipe. A commit message MUST:
- Start with a Conventional Commits header:
<type>(<scope>)?: <subject>(scope optional). - Contain a Linear issue ID (
<TEAM>-<NUM>, e.g.NON-45) somewhere — subject or body. - Use a Linear magic word + ID for the commit that should close the issue.
A commit message SHOULD keep the subject under 72 chars, imperative mood, no trailing period. Put the why in the body when the diff doesn't make it obvious.
Failure mode. Commits with no Linear linkage — months later, archaeology requires reading the diff itself because there's no ticket trail.
Subject describes the change; magic word lives in the body
Principle. The subject describes what changed; the Linear magic word goes in the body.
Why. "feat(auth): closes NON-45" looks tidy but conflates two things — what the commit does and what ticket it closes. The subject is the scannable description; the body is where automation hooks. Keeping the magic word in the body means the subject reads as a changelog entry, not a ticket-management instruction.
Recipe.
✓ feat(auth): add SSO callback handler
Closes NON-45.
✓ fix: prevent duplicate org invites (Fixes NON-87)
✓ refactor(forms): extract field registry — refs NON-103
✗ feat: add login flow
(no Linear ID anywhere — commit-msg hook rejects)
✗ feat(auth): closes NON-45
(subject is the magic word; subject should describe the change)
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 · 181 lines · 58 tokens per session scan A a0996c147c7e
factory-commits is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 2,108 once invoked, about $0.0003 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
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.
smart-commit
Create clean Conventional Commits: inspect the diff, group related changes, run quality checks, and write type(scope) messages. Use when committing work, or when the user runs /smart-commit or asks to commit changes.
kanso-commit
Use when the user asks to commit changes, stage their work, write commit messages, or split the working tree into logical commits.
dev-finish
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
commit
Use when the user asks to commit, create a git commit, checkpoint changes, save work to git, or write a commit message.
timesheet
Use when the user needs a monthly work summary, time-tracking report, or commit-based activity recap.