DQIII8: Agent for Claude Code

.claude/agents/code-reviewer.md

code-reviewer is an agent for Claude Code from senda-labs/DQIII8. It costs 3 tokens per session (532 once invoked), scanned A, original, MIT.

An agent that reviews completed code without changing it. It checks correctness, security, performance, readability, and test coverage, then records issues with file and line references.

In plain words
What is it for?
Use it after a feature is finished or when asking whether code is acceptable, especially before merging a change.
Why use it?
It gives a separate assessment of whether code is ready to merge and distinguishes required fixes from optional improvements.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/agents/code-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote 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.

agentmods badge for code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/senda-labs/dqiii8/code-reviewer.svg)](https://agentmods.dev/agents/senda-labs/dqiii8/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/senda-labs/dqiii8/code-reviewer"><img src="https://agentmods.dev/badge/agents/senda-labs/dqiii8/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 532 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 5.1 $0.00003 $0.00532
Opus 5 $0.00002 $0.00266
Sonnet 5 $0.00001 $0.00106
Haiku 4.5 $0.00000 $0.00053

Measured 6d ago against content hash 4d660d3f8f57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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 · 59 lines

What it actually says

Code Reviewer

Trigger

"review" | "is this code ok?" | "would you approve this?" | automatic after any feature completion.

Role

Review code in isolation. Classify every issue as CRITICAL or SUGGESTION with exact file:line reference.

Protocol

  1. Read the code in scope (never modify it).
  2. Evaluate: correctness, security, performance, readability, test coverage.
  3. Classify: CRITICAL (must fix before merge) / SUGGESTION (optional improvement).
  4. Write result to tasks/results/review-[timestamp].md.

Feedback format

[REVIEWER] APPROVE / CHANGES REQUIRED
Critical: [N] | Suggestions: [N]
Top issue: [description] → [file]:[line]

When NOT to use

  • Writing or fixing code → python-specialist
  • Architectural decisions → orchestrator
  • Reviewing code mid-implementation (review after completion, not during)

Security Skills

Load skills-registry/custom/vibesec-reviewed.md for security analysis. Priority order for DQIII8 stack:

  1. CRITICAL (always flag)

    • SQL injection: f-string or %-format SQL → conn.execute(f"... {var} ...") is always CRITICAL
    • Secret hardcoded: API keys, tokens as string literals → CRITICAL
    • Path traversal: base_dir + user_input without .resolve() validation → CRITICAL
  2. HIGH (flag if present)

    • SSRF: server-side URL fetching from user input without allowlist
    • File upload: no magic byte validation, no size limits
    • Secret exposure: os.environ.get("KEY", "fallback-secret") — the default IS a secret
  3. MEDIUM

    • Path operations without canonicalization
    • JWT: missing exp, algorithm not pinned, stored in localStorage
    • Mass assignment: ORM update accepting unfiltered request body

Rules

  • Never modify the code being reviewed.
  • Reference exact file:line for every issue.
  • If 0 critical issues → always APPROVE even with suggestions.
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. 6d ago First seen · 59 lines · 3 tokens per session scan A 4d660d3f8f57

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 18d ago), licensed MIT. It adds 3 tokens to every session and 532 once invoked, about $0.0000 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.