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 sliamh11/Deus --skill code-reviewgit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/sliamh11/deus/code-review)<a href="https://agentmods.dev/skills/sliamh11/deus/code-review"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/code-review/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/sliamh11/deus/code-review"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.02265 |
| Opus 5.5 | $0.00013 | $0.00906 |
| Sonnet 5.5 | $0.00007 | $0.00453 |
| Haiku 4.5 | $0.00003 | $0.00227 |
Grade A, and why
code-review scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run([sys.executable, 'evolution/cli.py', 'dismiss_review_finding', payload]) How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Code Review
Run a multi-agent code review on the current branch's PR. Three specialized agents (style, logic, security) review in parallel, findings are confidence-scored, and dismissed findings feed back into the evolution system as negative examples for future reviews.
Prerequisites
- Git — must be in a git repository
- GitHub CLI —
ghauthenticated - Current branch must have an open PR
Instructions
When the user asks for a code review or triggers this skill:
Step 1: Validate environment
git rev-parse --is-inside-work-tree # Must be in a repo
gh auth status # Must be authenticated
Get the current branch and find the open PR:
BRANCH=$(git branch --show-current)
gh pr list --head "$BRANCH" --state open --json number,title,baseRefName
If no PR exists, ask the user if they want to create one first. Do NOT proceed without a PR.
Step 2: Check eligibility
Skip review if:
- PR is a draft (
gh pr view <number> --json isDraft) - PR has zero code changes (only docs/config)
- This exact commit SHA was already reviewed (check
resources/review-history.logif it exists)
Step 3: Gather context
Collect all inputs the review agents will need:
# Get the unified diff
gh pr diff <number>
# Get file list and stats
gh pr view <number> --json files,additions,deletions
# Get PR description for intent context
gh pr view <number> --json body
Also load:
- CLAUDE.md files from the repo root AND from each modified directory (use Glob to find them)
- Review criteria from
resources/review-criteria.md(repo-specific rules) - Dismissed findings from
resources/dismissed-log.md(negative examples — "do NOT flag X when Y")
Step 4: Parallel review — launch 3 agents
Launch three review agents in parallel using the Task tool. Each agent receives:
- The PR diff
- Relevant CLAUDE.md content
- Review criteria for their domain
- Negative examples from dismissed-log.md for their category
- Instructions to output findings in a structured format
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 296 lines · 33 tokens per session scan A aeb32de3fa55
code-review is a skill published in the GitHub repository sliamh11/Deus (52 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 2,265 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pr-comment-evaluator
Use to judge whether a PR review comment sounds polite.
red-team-review
Unified adversarial review, two modes. Strategic Matrix v4.3 (MTA-004) for arguments/plans/decisions: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA → Blind Spot/Kill Switch → Summary. Deliverable Audit for built artefacts (assignments, reports, code outputs): isolated fresh-context hunt against the brief…
developer_review
Code-review workflow for repositories in a conversation's code folder.
agent-pipeline
Turn a review of code or docs into verified, actioned work with tiered agents. A cheap agent maps, a smart agent tags findings with predicted steps and a test written before any action, a skeptic verifies, a cheap agent acts in a sandbox, and the whole chain is reviewed afterwards with agent-review. Use for a sweep…
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.