submit-review

submit-review is a skill for Claude Code, Codex from tmj-90/gaffer. It costs 95 tokens per session (754 once invoked), scanned A, original, Apache-2.0.

A guide for handing a completed ticket to human review in a software delivery workflow. It explains how to verify acceptance criteria, run checks, commit the work, and stop for the delivery runner.

In plain words
What is it for?
Checking ticket evidence, running tests and linting, making the required commit, and preparing finished work for review.
Why use it?
It prevents incomplete or unverified work from being submitted and clarifies which delivery steps belong to the agent versus the runner.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/tmj-90/gaffer/submit-review
Any agent
npx skills add tmj-90/gaffer --skill submit-review
Clone the repo
git clone --depth 1 https://github.com/tmj-90/gaffer

Made for: Claude Code, Codex.

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 submit-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/tmj-90/gaffer/submit-review.svg)](https://agentmods.dev/skills/tmj-90/gaffer/submit-review)
Your own site
<a href="https://agentmods.dev/skills/tmj-90/gaffer/submit-review"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/submit-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 754 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 5.1 $0.00095 $0.00754
Opus 5 $0.00048 $0.00377
Sonnet 5 $0.00019 $0.00151
Haiku 4.5 $0.00010 $0.00075

Measured 2d ago against content hash 5825d3774e42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

submit-review 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 2d 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.

runner/skills/submit-review/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handing a ticket to review (runner-owned)

You do not submit your own work. In the Gaffer factory the runner — not the agent — owns delivery bookkeeping: after your agent run it runs the gates (tests/lint/hygiene/minimalism), records the delivery, pushes the branch and opens the PR when a remote exists, and moves the ticket to in_review. This makes submission deterministic and token-free, and guarantees a ticket is only ever submitted once its gates are green.

What YOU do (then stop)

  1. Confirm every AC is evidenced. Call get_ticket (Dispatch MCP) and check each AC has true evidence. If any is missing, record it via the record-evidence skill.
  2. Confirm the gates are green in this session: tests (run-tests), lint (run-lint), and any coverage threshold the ticket requires. Fix anything red.
  3. Commit on the feature branch with a clear conventional message referencing the ticket (git add -A && git commit -m "deliver #<n>: <summary>"). An uncommitted edit is NOT a delivery — the branch must carry your commit. If you forget, the runner auto-commits your uncommitted changes as a safety net, but commit yourself.
  4. Stop. Do not push, do not open a PR, do not call submit_ticket_for_review. The runner does all of that. If you cannot finish (open question, missing dependency, failing environment), call mark_ticket_blocked with a clear reason instead of leaving half-done work.

What the RUNNER does (not you)

  • Runs the Definition-of-Done and hygiene/minimalism gates on your committed diff.
  • Records the delivery (branch + diff summary + per-repo delivery rows).
  • Pushes the branch and opens the PR (gh pr create) when the repo has a remote.
  • Submits the ticket for review (moves it to in_review).

Rules

  • Never self-approve done or merge — only a human does, after review.
  • Never push, open a PR, or submit_ticket_for_review yourself — that is the runner's job.
  • Don't consider yourself done until every AC has real evidence and the gates are green — the runner's gates will bounce a delivery that isn't.

Read the full file on GitHub · 53 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. 2d ago First seen · 53 lines · 95 tokens per session scan A 5825d3774e42

Subscribe to this mod's changes

submit-review is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 95 tokens to every session and 754 once invoked, about $0.0005 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 2026-09-03.