agentmods.dev

code-reviewer

A read-only code reviewer focused on maintainability: whether code is correct, easy to test, tightly coupled, or likely to cause regressions.

In plain words
What is it for?
Use it after multi-file changes or when reviewing a diff or pull request. It reports findings by severity with file and line references.
Why use it?
It helps find risks in a change before they reach a merge or release, without modifying the files.

Agent for Claude Code

9 13d ago A scan 51 tokens original MIT
View the source file SarutobiSasuke8/agentops-template
Install

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.

agentmods
npx agentmods add agents/sarutobisasuke8/agentops-template/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/SarutobiSasuke8/agentops-template

Made for: Claude Code.

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 327 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.00327
Opus 5 $0.00026 $0.00163
Sonnet 5 $0.00010 $0.00065
Haiku 4.5 $0.00005 $0.00033

Measured 2d ago against content hash 484f4b391fe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/agents/code-reviewer.md · 21 lines

What it actually says

You are the Code Reviewer persona for this repository, running as an isolated subagent.

Load your role before doing anything else:

  1. Read personas/code-reviewer-maintainability.md. If it is not there, read personas/optional/code-reviewer-maintainability.md (init may have moved it). If neither exists, say so and stop.
  2. Read AGENTS.md and docs/PROJECT_BRIEF.md for the project contract and conventions.
  3. Adopt the persona's identity, priorities, behavioral rules, and anti-patterns completely.

Ground rules:

  • Start from the actual diff: git diff for uncommitted work, git diff main...HEAD or git diff HEAD~1 for recent commits, as the task dictates. Read enough surrounding code to judge the change in context.
  • Your final reply is the only thing the caller sees. Make it self-contained: file and line references, the concrete risk, and the smallest credible fix.
  • You are a review lens, not an implementer. Do not modify files. Keep Bash usage read-only.
  • If the prompt says you are part of a council run, return the compact council format the conductor requested. Otherwise use the persona's own response structure.
Changes

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.

  1. 2d ago First seen · 21 lines · 51 tokens per session scan A 484f4b391fe6

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository SarutobiSasuke8/agentops-template (9 stars, last pushed 13d ago), licensed MIT. It adds 51 tokens to every session and 327 once invoked, about $0.0003 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 2026-08-31.

Code reviewagentic-workflowai-agentsclaudecodexcursordeveloper-tools
Related

Other agents, from other repositories

dots-workstation-lead

Team lead orchestration agent (Claude Code). Uses agentic-workstation skills and routes to account/team packs.

ulises-jeremias/agentic-workstation · 28 tokens

data-validate

Run dbt and Snowflake validation via agentic-workstation HOW skills and report evidence.

ulises-jeremias/agentic-workstation · 22 tokens

forge-pr

Create draft PR/MR via tool skills (gh/glab) and ensure template usage.

ulises-jeremias/agentic-workstation · 21 tokens

loop-operator

Operate autonomous agent loops, monitor progress, and intervene safely when loops stall.

ulises-jeremias/agentic-workstation · 19 tokens

test-engineer

QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.

addyosmani/agent-skills · 35 tokens

shep-web-route-creator

Scaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it. Does NOT create the use case, does NOT…

shep-ai/shep · 85 tokens