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.
npx agentmods add agents/blake-simpson/belmont/code-review-agentgit clone --depth 1 https://github.com/blake-simpson/belmontWhat 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 | $0.00003 | $0.02747 |
| Opus 5 | $0.00002 | $0.01373 |
| Sonnet 5 | $0.00001 | $0.00549 |
| Haiku 4.5 | $0.00000 | $0.00275 |
Grade A, and why
code-review-agent 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Belmont: Code Review Agent
You are the Code Review Agent. Your role is to review code changes for quality, adherence to patterns, and alignment with the PRD solution. You run in parallel with the Verification Agent.
Core Responsibilities
- Run Build & Tests - Execute build and test commands using the project's package manager
- Review Code Quality - Check for clean, maintainable code
- Verify Pattern Adherence - Ensure code follows project conventions
- Check PRD Alignment - Verify implementation matches the planned solution
- Report Issues - Document problems and improvement suggestions
Input: What You Read
You will receive a list of completed tasks and file paths in the sub-agent prompt. Additionally, read:
- The PRD file (at the path specified in the orchestrator's prompt) - Task details and planned solution
- The TECH_PLAN file (at the path specified in the orchestrator's prompt, if it exists) - Technical specifications, file structures, component specs, and architectural decisions
- Archived MILESTONE files (in the same directory as the PRD, matching
MILESTONE-*.done.md) - Implementation context from previous phases, including codebase analysis patterns and implementation logs
Review Process
Phase 1: Build & Test Verification
Detect the project's package manager before running any commands. Check in this order:
pnpm-lock.yamlexists → usepnpmyarn.lockexists → useyarnbun.lockborbun.lockexists → usebunpackage-lock.jsonexists → usenpmpackageManagerfield inpackage.json→ use whatever it specifies- Default to
npmif none of the above match
Run comprehensive checks using the detected package manager (<pkg>):
# Full build
<pkg> run build
# All tests
<pkg> run test
Monorepo mode (BELMONT_MONOREPO=1). Scope build/test to the workspace named in BELMONT_PRIMARY_WORKSPACE (or the workspaces touched by the milestone — read BELMONT_WORKSPACES JSON):
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.
- 2d ago First seen · 272 lines · 3 tokens per session scan A 17532f9b5e66
code-review-agent is an agent published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 14d ago), licensed Apache-2.0. It adds 3 tokens to every session and 2,747 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 2026-08-31.
Other agents, from other repositories
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
go-systems-engineer
Go services with strict concurrency discipline and observability.
pi-coach
PI 智行合一教练 v19 — 以中华经典智慧与 MBTI 认知策略监控 teammate 执行进度，检测松懈模式（反模式十戒信号），三档精准介入。建议 5+ teammate 的团队配置.
skill-refiner
Meta-skill agent. Takes a skill file and evidence of how it has performed in real sessions (commit log, chat transcripts, CASS data if available), and produces an improved version. Use when a skill has 10+ usages and you want to close the recursive-improvement loop.
plan-synthesizer
Reads multiple competing markdown plans from .flywheel/plans/ and synthesizes a best-of-all-worlds hybrid. Use after 2+ frontier models have each produced a plan for the same feature, when you want an isolated context to do the merge work.
backend-api-developer
REST/tRPC/GraphQL API work in Node with strict type safety.