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 osouthgate/agent-plus --skill code-reviewergit clone --depth 1 https://github.com/osouthgate/agent-plusWrote 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/osouthgate/agent-plus/code-reviewer)<a href="https://agentmods.dev/skills/osouthgate/agent-plus/code-reviewer"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus/code-reviewer/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/osouthgate/agent-plus/code-reviewer"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus/code-reviewer.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 | $0.00042 | $0.01607 |
| Opus 5.5 | $0.00017 | $0.00643 |
| Sonnet 5.5 | $0.00008 | $0.00321 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
code-reviewer 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 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.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-reviewer
Reviews changed code only. Flags bugs, security issues, rule violations, reuse opportunities, and simplification options. The goal is fewer lines, fewer concepts, and correct behavior — not more code.
When invoked
- Get scope when unclear — If no diff and no files indicated, ask: "Review uncommitted changes, a branch diff, or specific files?" Do this before any other step.
- See what changed —
git diffor the files the user points to. Focus on modified and new code only; do not flag pre-existing untouched code. - Read full context — Open and read the full file(s) for changed areas before flagging anything.
- Check applicable project rules — Identify which rules, conventions, or style guides apply (check
.cursor/rules/,AGENTS.md, or similar). Verify changed code complies; flag violations with the rule name or path. - Check for existing code and simplify — For new functions, queries, or UI: does the codebase already have something that does this (or could with a small change)? Flag as a refactor opportunity. Also flag: unnecessary helpers, over-abstraction, code that could be inlined or removed.
- Check security, auth, and validation — For new or changed server code, API routes, or protected endpoints: is authentication required and applied consistently? Is input validation done via appropriate helpers rather than ad-hoc in handlers? Admin-only paths properly restricted? Flag missing or incorrect auth/validation as Critical or Warning.
- Review against criteria below — Bugs first, then security/auth/validation, then rule compliance, reuse/refactor and simplification opportunities, then structure, performance (especially DB queries and server-side code), project conventions.
- Consider test recommendations — For new or changed logic: does it warrant tests (branching, transactions, side effects, non-trivial validation)? If yes, add a Test recommendations section. Don't recommend tests for thin pass-throughs or constants.
- Recurring gaps — If the same kind of problem appears multiple times, or a gap isn't covered by existing rules, add a Config follow-up section recommending a new or updated rule or lint entry.
- Security deep-dive — If Critical or multiple Warnings in security/auth are flagged, note that the user may want a focused security audit, or invoke the security-reviewer skill if present.
WebFetchis available for looking up CVEs or checking a library's changelog when assessing a security finding.
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 · 83 lines · 42 tokens per session scan A df00481d3aab
code-reviewer is a skill published in the GitHub repository osouthgate/agent-plus (4 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,607 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
goal-test
A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.
commit
A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.
create-task
This skill should be used when creating a task in the active tracker - "create task", "create issue", "bd create", "new task", "add task", "add issue". Ensures all required fields are provided, enforces English-only task content, and suggests epic labels. Triggers on any task creation in any context - commands…
loop-gh-pr
A recipe for a scheduled GitHub pull-request watcher. It checks open pull requests for new activity and prepares read-only review drafts without posting comments or merging anything.
agent-report
Internal skill for commands. The file transport for agent reports - hand every Task-dispatched agent a REPORTFILE, then collect every report in full and fail loudly on a missing one. Do not trigger on user conversation - only when a command dispatches agents.
goal-plan-clean
A guide for creating a reusable plan-review loop. It repeatedly checks a plan, fixes blocking issues and suggestions, and stops after approval or a small number of review rounds.