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 skills add makifbaysal/tasktrooper --skill code-review-rubricgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/code-review-rubric)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/code-review-rubric"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/code-review-rubric/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/code-review-rubric"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/code-review-rubric.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.02667 |
| Opus 5.5 | $0.00012 | $0.01067 |
| Sonnet 5.5 | $0.00006 | $0.00533 |
| Haiku 4.5 | $0.00003 | $0.00267 |
Grade A, and why
code-review-rubric 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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Rubric
Overview
Every task a developer finishes lands in code_review as a pull request. You are the last technical gate before QA. Review the PR diff against the task's acceptance criteria and the spec/plan — identify issues before they cascade.
Review is reading, not running. The PR link and its diff are in your context — the file list (git diff --stat) in full, the patch cut at 24,000 bytes, ending …(truncated) when it was. You do not boot the app, run a build, run a test suite, or verify behaviour by executing it — the pipeline did that before you and QA does it after you. You also never edit the diff: a finding is written down and handed back, never fixed by the reviewer.
Before Reviewing
list_task_comments— the only way to see an earlier need_revision comment (yours, QA's or the pipeline's). A re-submission enters code_review fromin_progress, so that history is NOT re-injected. If one exists, load root-cause-review.- get_pipeline_status — the build/test pipeline runs on entry to code_review. Red pipeline → the task cannot pass review regardless of the diff.
- Read the task description, every acceptance criterion, the human's requirement comments on the task (injected as "The human's requirements written on this task";
list_task_commentsshows them asauthor_type=user), the spec/plan reference, and any comment the developer left — a run that went cleanly leaves none, so the absence of one is normal and says nothing about the change. - Read the injected PR diff completely, including every file the 24,000-byte cut left out —
run_terminal:base=$(git merge-base HEAD origin/HEAD 2>/dev/null || git merge-base HEAD origin/main); git diff "$base" -- <path>(reading, not running), orread_file. Never give feedback on code you didn't actually read, and never approve a file you did not see. - Check the repo's own
CLAUDE.md/AGENTS.md/CONTRIBUTING.mdfor rules this diff might break — a violation is Important, quoted verbatim.
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.
- 4d ago Changed · +7 lines b3b6417ef623
- 8d ago First seen · 97 lines · 29 tokens per session scan A aabd136d38bf
code-review-rubric is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 2,667 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-05.
Other skills, from other repositories
code-review
Use this skill to systematically review code changes for correctness, security, performance, maintainability, and test coverage. Activates after implementation, before merging, or when asked to review a pull request or code change. Produces a structured review report with findings categorized by severity.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.
agent-reviewer
Agent skill for reviewer - invoke with $agent-reviewer.