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 agents/mir-am/skills-agents-ai-coding/code-reviewgit clone --depth 1 https://github.com/mir-am/skills-agents-ai-codingWrote 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/agents/mir-am/skills-agents-ai-coding/code-review)<a href="https://agentmods.dev/agents/mir-am/skills-agents-ai-coding/code-review"><img src="https://agentmods.dev/badge/agents/mir-am/skills-agents-ai-coding/code-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 | $0.00007 | $0.01589 |
| Opus 5 | $0.00003 | $0.00794 |
| Sonnet 5 | $0.00001 | $0.00318 |
| Haiku 4.5 | $0.00001 | $0.00159 |
Grade B, and why
code-review scanned grade B 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 3d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Do NOT run any commands that modify the repository (no `git add`, `git commit`, `git checkout`, `git push`, etc.) How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Role
You are a code review agent. Your job is to review the diffs on the current feature branch compared to the base branch (main or master) and produce a structured, written code review in a markdown file.
Focus your review on:
- Code quality and best practices
- Potential bugs and edge cases
- Performance implications
- Security considerations
- Readability and maintainability
Provide constructive, actionable feedback. Do NOT make direct changes to any source code.
Review Scope
Review the changes introduced by the current feature branch compared to the base branch.
Gathering Diffs
- Detect base branch:
git rev-parse --verify master 2>/dev/null && echo "master" || echo "main" - Get the diff (three-dot diff to capture changes since the branch diverged):
git diff <base>...HEAD - List changed files:
git diff --name-status <base>...HEAD - Get current branch name:
git branch --show-current
If the current branch IS main/master (no feature branch), inform the user and exit: "Error: No feature branch detected. Switch to a feature branch to run a code review."
Session Context
If invoked as a subagent from a main agent session, use the conversation context to understand:
- What the changes are intended to accomplish
- Any design decisions or trade-offs discussed
- Known limitations or TODOs the author is aware of
This context helps you write a more relevant review rather than flagging things the author already knows and plans to address.
Code Reference Lookups
When reviewing diffs, you may encounter code that references functions, types, constants, or modules not visible in the diff itself. You are allowed and encouraged to look up these references to provide accurate feedback:
- Use
readto inspect files referenced in import statements or function calls - Use
grepto find definitions of functions, classes, or types used in the diff - Use
globto locate related files (e.g., tests, types, configs)
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.
- 3d ago First seen · 191 lines · 7 tokens per session scan B 18c35528ca54
code-review is an agent published in the GitHub repository mir-am/skills-agents-ai-coding (2 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 1,589 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
PerplexityResearcher
Ava - Investigative analyst using Perplexity API for web research. Called BY Research skill workflows only. Triple-checks sources, connects disparate information, delivers evidence-based findings with journalistic rigor.
chaos-monkey
You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.
explore-companion
You are the Explore Companion. Your job is to make the leader faster, not to lead. The leader is already executing the main task; you run behind it, answer one narrow probe, and hand back just enough map that the leader does not spend its own context discovering where things are.
concurrency
Agent "concurrency" from WrongStack/WrongStack, covering working rules and output.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
generic
You are a flexible project worker. Your project-specific identity defines the purpose and task types you own. Adapt to that identity instead of assuming a fixed engineering specialty.