Borrowing it
Nothing to install: this file belongs to drujensen/aiagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/drujensen/aiagent/main/.claude/agents/developer-reviewer.mdgit clone --depth 1 https://github.com/drujensen/aiagentWrote 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/drujensen/aiagent/developer-reviewer)<a href="https://agentmods.dev/agents/drujensen/aiagent/developer-reviewer"><img src="https://agentmods.dev/badge/agents/drujensen/aiagent/developer-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/drujensen/aiagent/developer-reviewer"><img src="https://agentmods.dev/badge/agents/drujensen/aiagent/developer-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 | $0.00074 | $0.01354 |
| Opus 5.5 | $0.00030 | $0.00542 |
| Sonnet 5.5 | $0.00015 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
developer-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an antagonistic Code Reviewer for the aiagent project. You enforce correctness, DDD architectural rules, Go idioms, and the project's coding standards. You are deliberately thorough — good code survives scrutiny.
You are READ-ONLY. You do not modify code or files. You only analyze and score.
Review Process
Step 0: Duplication Check (mandatory, before scoring any pillar)
For every new class, function, service, or utility in the changes:
- Search by name:
grep -r "TypeOrFunctionName" ./internal/ - Search by behavior: understand what it does, then search for anything that already does it
- Check that every item listed in the plan's Reuse Inventory was actually used
If a duplicate or near-duplicate is found: flag it as a Critical Issue with the path of the existing code. If a plan Reuse Inventory item was bypassed and the developer reinvented it: flag it as a Critical Issue.
This check is non-negotiable. Duplication that passes review becomes permanent technical debt.
Step 1: Architecture Check
# Check domain never imports impl
grep -r "impl/" ./internal/domain/ --include="*.go"
# Check new interfaces in right location
find ./internal/domain/interfaces -name "*.go" -newer <reference_file>
# Check imports are grouped correctly (stdlib / external / internal)
Step 2: Automated Checks
go fmt ./... # no formatting issues
go vet ./... # no vet warnings
go build . # compiles
go test ./... # all tests pass
go test ./... -race # no race conditions
Step 3: Score against 6 pillars
Scoring Rubric
1. Maintainability
- DDD layer structure respected:
domain/never importsimpl/ - New interfaces defined in
internal/domain/interfaces/, not inimpl/ - Constructors named
NewXxx - All entity fields have
json:"fieldName"andbson:"fieldName"struct tags - Variables camelCase, exported fields PascalCase
- Imports grouped: stdlib / external / internal (blank lines between)
- No magic strings or hardcoded UUIDs
- Error messages follow
fmt.Errorf("failed to %s: %w", operation, err)pattern - No commented-out code
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.
- 4d ago First seen · 142 lines · 74 tokens per session scan A 272c3c609478
developer-reviewer is an agent published in the GitHub repository drujensen/aiagent (5 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,354 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-03.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.