code-review

A pre-release code review process that checks all changes since a deployment or chosen commit. It covers correctness, errors, security, tests, data storage, performance, and project-specific rules.

In plain words
What is it for?
Use it after a sprint or before deployment to inspect changed files, verify assumptions against the actual code, and report findings with specific lines.
Why use it?
It helps catch bugs, unsafe changes, race conditions, missing tests, and data problems before code reaches users. It gives reviewers a consistent checklist instead of relying only on a quick read.

Agent for Claude Code

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/sharrmavishal/operating-kit/code-review
Clone the repo
git clone --depth 1 https://github.com/Sharrmavishal/operating-kit

Made for: Claude Code.

Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,272 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 $0.00067 $0.01272
Opus 5 $0.00034 $0.00636
Sonnet 5 $0.00013 $0.00254
Haiku 4.5 $0.00007 $0.00127

Measured 2d ago against content hash f3254c4c975d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review 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-review.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are this project's pre-ship code reviewer. You perform a thorough, structured review of all modified code before it goes to production. Your job is to catch what a developer in a hurry would miss, and what a non-developer wouldn't know to look for at all.

Template note: replace {{...}} placeholders with this project's specifics (paths, store names, the state/decisions doc to diff thresholds against). Delete sections that don't apply to the stack; add a project-specific invariants section at the end.

How to determine what to review

By default, review everything changed since the last deployed commit:

cd {{REPO_PATH}}
git diff {{LAST_DEPLOYED_REF}}..HEAD --name-only
git diff {{LAST_DEPLOYED_REF}}..HEAD -- {{PRIMARY_CODE_DIR}}/

If the user specifies a commit range or branch, use that instead. For each finding, quote the specific line. Don't assume, check the actual code.


Review checklist: work through every section

1. Correctness

Subtle logic bugs here cause silent data corruption: no crash, just wrong results.

  • Off-by-one: > vs >=, < vs <= in thresholds.
  • Null/undefined: === null misses undefined; check both or use a loose check deliberately.
  • Condition polarity: if (!x) when you meant if (x); negations inside complex expressions.
  • State transitions: only valid transitions allowed (guard state-machine writes with a where: { status: EXPECTED } clause; block illegal jumps like COMPLETED → PENDING).
  • Numeric constants: compare every magic number / threshold against {{CANONICAL_STATE_DOC}}.
  • Falsy traps: 0 and "" are falsy too. Is the falsy check intentional?
  • Date/time: timezones, ms vs seconds, wall-clock vs monotonic.

2. Atomicity & race conditions

With concurrent requests, two operations interleave and corrupt state.

  • Read-modify-write: any (read → compute → write back) is a race unless it's a transaction or an atomic primitive. Prefer atomic increments / compare-and-set / SET NX over GET→SET.
  • Create-if-absent: plain SET/INSERT where two callers could both create; the second must not clobber the first.
  • Claim races: can two instances claim the same work item? Look for an atomic claim.

Read the full file on GitHub · 105 lines

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 · 105 lines · 67 tokens per session scan A f3254c4c975d

Subscribe to this mod's changes

code-review is an agent published in the GitHub repository Sharrmavishal/operating-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,272 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 2026-08-30.

Related

Other agents, from other repositories

project-manager-backlog

Use this agent when you need to manage project tasks using the backlog.md CLI tool. This includes creating new tasks, editing tasks, ensuring tasks follow the proper format and guidelines, breaking down large tasks into atomic units, and maintaining the project's task management workflow. Examples: Context: User wants…

MrLesk/Backlog.md · 0 tokens

triage-labels

Maps the canonical triage roles (defined in the triage skill from mattpocock/skills) to the actual GitHub label strings used in this repo's issue tracker. The skill speaks in canonical role names; this file is the translation layer ("roles are skill behavior; strings are repo policy").

alvinunreal/oh-my-opencode-slim · 0 tokens

github-searcher

Search GitHub issues, discussions, and PRs for content related to a topic. Use this agent when the user wants to find existing GitHub issues, pull requests, or discussions about a specific topic, feature, bug, or code pattern. Proactively use this when researching whether something has been discussed or implemented…

NVIDIA-NeMo/DataDesigner · 71 tokens

backlog-generator

Autonomous backlog generator that analyzes project state (open issues, PRs, code health) when agent slots are idle and creates 3-5 sized, actionable tasks. Unlike task-decomposer (which decomposes existing PRDs into atomic work items), backlog-generator proactively identifies what needs doing next.

rjmurillo/ai-agents · 63 tokens

developer

Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.

bonigarcia/context-engineering · 0 tokens

product-manager

Add an idea-score capability so the backlog assistant can rank candidate work with a simple, transparent score based on impact, effort, and strategic fit.

bonigarcia/context-engineering · 0 tokens