factory-submit

factory-submit is a skill for Claude Code, Codex from nonlinear-xyz/factory-kit. It costs 15 tokens per session (683 once invoked), scanned A, original, MIT.

A procedure for moving a Linear issue, which is a project-tracking ticket, into the team’s “In Review” state.

In plain words
What is it for?
It helps find the issue from a supplied identifier or the current Git branch, read its current status, confirm the match, and then update it.
Why use it?
It prevents the wrong ticket from being moved and makes clear that review status changes are separate from pushing code or opening a pull request.

Skill for Claude CodeCodex

Part of the factory-kit plugin — 37 skills, 8 commands, 12 agents, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/nonlinear-xyz/factory-kit/factory-submit
Any agent
npx skills add nonlinear-xyz/factory-kit --skill factory-submit
Clone the repo
git clone --depth 1 https://github.com/nonlinear-xyz/factory-kit

Made for: Claude Code, Codex.

Or install factory-kit, the plugin that ships this one along with the rest of its 37 skills, 8 commands, 12 agents, 1 MCP server.

Wrote 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.

agentmods badge for factory-submit

README.md
[![agentmods](https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-submit.svg)](https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-submit)
Your own site
<a href="https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-submit"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-submit.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00683
Opus 5 $0.00008 $0.00342
Sonnet 5 $0.00003 $0.00137
Haiku 4.5 $0.00002 $0.00068

Measured 3d ago against content hash 6949074e75c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

factory-submit 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 3d 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.

skills/factory-submit/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You're handing a ticket off to review. This command moves it to the team's "In Review" state in Linear. It does not push code, open a PR, or change git state — those are separate steps the user owns.

Invocation input: an optional issue identifier. If omitted, auto-detect it from the current branch name.

What to do

  1. Read project configuration. Prefer .factory-kit/linear.json; use legacy .claude/linear.json only as a migration fallback. If neither exists, stop and direct the user to setup-linear. Pull teamKey and states.inReview (default "In Review").

  2. Resolve the issue ID.

    • If invocation input is provided: normalize it (prepend <teamKey>- if numeric).
    • Otherwise: get the current branch with git rev-parse --abbrev-ref HEAD. Match against (\d+) and construct <teamKey>-<num> from the first numeric chunk after the team key (case-insensitive). Example: nishu/non-45-setup-scaffoldNON-45.
    • If no issue ID can be derived, ask the user for it. Don't guess.
  3. Confirm before mutating.

    • Fetch the issue through the connected Linear integration and show: <KEY-N> — title (current state: <state>).
    • Ask the user to confirm the move. If the current state is already In Review, say so and stop.
  4. Move the issue. Use the Linear integration's issue-update capability with id and state set to the configured inReview value. If the integration requires a state UUID, list team statuses and resolve the configured name first.

  5. Post a handoff comment (optional but default-on). Before flipping state, draft a short comment in the factory-voice.md shape so the reviewer knows what they're looking at. Density matters — links into the decision graph (PR, related issues, prior comment threads) are what make the comment useful six months later.

    **Outcome:** <one sentence — what this branch does>
    **Why:** <the underlying constraint or principle>
    **Tradeoff:** <if any>
    **Refs:** <PR URL, related issue IDs, last commit SHA if no PR>
    

    Show the draft, ask for approval, then post it through the Linear integration's comment capability. Skip this step if the invocation input includes --no-comment or the issue already has a recent comment from this branch.

  6. Confirm completion. Print <KEY-N> moved to In Review. That's it — no PR side effects.

Read the full file on GitHub · 42 lines

Changes

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.

  1. 3d ago First seen · 42 lines · 15 tokens per session scan A 6949074e75c3

Subscribe to this mod's changes

factory-submit is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 683 once invoked, about $0.0001 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.