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/tmj-90/gaffer/submit-reviewnpx skills add tmj-90/gaffer --skill submit-reviewgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/submit-review)<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>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 | $0.00095 | $0.00754 |
| Opus 5 | $0.00048 | $0.00377 |
| Sonnet 5 | $0.00019 | $0.00151 |
| Haiku 4.5 | $0.00010 | $0.00075 |
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.
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)
- Confirm every AC is evidenced. Call
get_ticket(Dispatch MCP) and check each AC has true evidence. If any is missing, record it via therecord-evidenceskill. - Confirm the gates are green in this session: tests (
run-tests), lint (run-lint), and any coverage threshold the ticket requires. Fix anything red. - 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. - 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), callmark_ticket_blockedwith 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
doneor merge — only a human does, after review. - Never push, open a PR, or
submit_ticket_for_reviewyourself — 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.
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.
- 2d ago First seen · 53 lines · 95 tokens per session scan A 5825d3774e42
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.
Other skills, from other repositories
dedup
Dedupe-only pass for BASESHA..HEAD: remove duplicate code introduced by the diff or reuse existing shared utils; applies changes + commits.
besimple-tiny-broccoli
Small-change wrapper: implement → run repo checks → atomic commit → run dedup (BASESHA..HEAD).
claude-simplify-wrapper
Run Claude's built-in /simplify skill on BASESHA..HEAD, validate checks, and commit.
plan-critique-loop
Critique and revise an existing plan doc up to 3 iterations, using accept/reject triage and stopping early when no important feedback remains. Use when refining a plan/.md before implementation.
high-quality-commit
コード変更を適切なgitコミット戦略でgit commitします。基本的には既存のgitコミットへのsquash戦略を採用し、必要に応じてブランチ全体のgitコミット履歴を再構成します。実装完了時やユーザーがgit commitを依頼した時に使用します。.
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.