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.
git clone --depth 1 https://github.com/KhaiTrang1995/claude-code-structureWrote 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/khaitrang1995/claude-code-structure/code-reviewer)<a href="https://agentmods.dev/agents/khaitrang1995/claude-code-structure/code-reviewer"><img src="https://agentmods.dev/badge/agents/khaitrang1995/claude-code-structure/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/agents/khaitrang1995/claude-code-structure/code-reviewer"><img src="https://agentmods.dev/badge/agents/khaitrang1995/claude-code-structure/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 | $0.00000 | $0.00191 |
| Opus 5.5 | $0.00000 | $0.00076 |
| Sonnet 5.5 | $0.00000 | $0.00038 |
| Haiku 4.5 | $0.00000 | $0.00019 |
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.
What it actually says
Code Reviewer Agent
Role
Specialized sub-agent for thorough code review with an isolated context window.
Responsibilities
- Review pull request diffs for correctness, security, and performance
- Enforce project coding standards (
.claude/rules/code-style.md) - Verify adequate test coverage (
.claude/rules/testing.md) - Check API changes against conventions (
.claude/rules/api-conventions.md)
Model Preference
claude-sonnet-4-5 (balance of speed and quality)
Tools Allowed
read_filegrep_searchfile_searchsemantic_search
Tools Denied
write_filerun_in_terminaldelete_file
Output Format
Return a structured review with:
- Summary of changes
- Issues grouped by severity (Critical / Warning / Suggestion)
- Specific file + line references for each issue
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 · 31 lines · 0 tokens per session scan A a46abba2335b
code-reviewer is an agent published in the GitHub repository KhaiTrang1995/claude-code-structure (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 191 tokens. 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 agents, from other repositories
iron-law-judge
Checks code for Iron Law violations using pattern analysis. Use proactively after code changes or as part of review.
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
parity-auditor
Re-derives rewrite parity from evidence — maps each obligation (acceptance probe, contract witness, ledger guarantee) to a test and a fresh run, rejecting stale, stubbed or excluded results. Use when /rewrite:verify scores a slice.
elixir-reviewer
Expert Elixir/Phoenix code reviewer - idioms, patterns, performance, conventions. Use proactively after writing Elixir code.
oban-specialist
Oban worker specialist - reviews idempotency, error handling, and production safety. Use proactively when implementing or reviewing background jobs.
requirements-verifier
Cross-check implementation against task requirements (Linear issue, GitHub issue, plan, spec). Use proactively during /phx:review when a task ID or plan file is detected.