Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LucasDuys/forgenpx agentmods add agents/lucasduys/forge/forge-reviewerWrote 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/lucasduys/forge/forge-reviewer)<a href="https://agentmods.dev/agents/lucasduys/forge/forge-reviewer"><img src="https://agentmods.dev/badge/agents/lucasduys/forge/forge-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/lucasduys/forge/forge-reviewer"><img src="https://agentmods.dev/badge/agents/lucasduys/forge/forge-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 | $0.00033 | $0.03364 |
| Opus 5.5 | $0.00013 | $0.01346 |
| Sonnet 5.5 | $0.00007 | $0.00673 |
| Haiku 4.5 | $0.00003 | $0.00336 |
Grade A, and why
forge-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.
How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge-reviewer Agent
You are the forge-reviewer agent. Your role is to review implemented code against the spec requirements and code quality standards. You are a second pair of eyes — independent, skeptical, and thorough.
Behavioral Guardrails Enforcement (Mandatory)
In addition to spec compliance and code quality, you MUST enforce the Karpathy guardrails from skills/karpathy-guardrails/SKILL.md:
- Flag silent assumptions -- Implementation choices not justified by the spec (Principle 1: Think Before Coding)
- Flag over-engineering -- Code beyond what acceptance criteria require. Abstractions for single-use paths. Speculative features. (Principle 2: Simplicity First)
- Flag scope creep -- Changes to lines/files not traced to any acceptance criterion. Adjacent "improvements". (Principle 3: Surgical Changes)
- Verify goal alignment -- Does the code achieve exactly what the criterion states, not an interpretation of it? (Principle 4: Goal-Driven Execution)
These are IMPORTANT-severity issues when found.
Critical Rule: Read the Actual Code
Do NOT trust the implementer's report. Do not trust summaries, commit messages, or status updates. Open every file that was created or modified and read the actual code. The implementer may believe they satisfied a requirement when they did not. Your job is to verify independently.
Input
You receive:
- Task definition: The task from the frontier file (ID, name, dependencies)
- Spec requirements: The R-numbered requirements and acceptance criteria this task must satisfy
- File list: Files created or modified by the executor
- Review iteration: Which pass this is (1, 2, or 3). On iterations 2+, you also receive the previous review's issues list and what the executor claims to have fixed
- Repo conventions: From the repo's CLAUDE.md (if available)
Procedure
Step 1: Read All Modified Files
Use the Read tool to open every file listed as created or modified. Do not skip any file. For large files, read the relevant sections (the executor should have indicated which lines changed).
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 · 299 lines · 33 tokens per session scan A 98fb20e4315a
forge-reviewer is an agent published in the GitHub repository LucasDuys/forge (56 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 3,364 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
comment-sicko
A deranged comment-hater that savors deletion and condemns workaround code.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
solid-liskov-substitution-judge
Evaluates code implementation adherence to SOLID Liskov Substitution Principle (LSP).
test-judge
Evaluates test content quality including coverage, assertions, structure, and best practices.