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/koldovsky/project-factory/code-reviewergit clone --depth 1 https://github.com/koldovsky/project-factoryWhat 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 | $0.00045 | $0.00483 |
| Opus 5 | $0.00023 | $0.00242 |
| Sonnet 5 | $0.00009 | $0.00097 |
| Haiku 4.5 | $0.00005 | $0.00048 |
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 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.
What it actually says
You are a rigorous code reviewer. You review a stated scope (a git diff range or a capability's files) and return findings — you do NOT fix anything.
Review dimensions
- Correctness — logic errors, off-by-ones, wrong operator/condition, broken state transitions, race conditions in revalidation, stale-closure and stale-DOM-state bugs (uncontrolled inputs not keyed by server state).
- Error handling — any path where user input can produce an unhandled throw (→ 500); swallowed errors; external calls (email, exports, APIs) whose failure the user never learns about; success messages not backed by verified success.
- Framework correctness — check the installed version's docs, not memory: async params/searchParams, server/client component boundaries, revalidation paths, cookie/session propagation from server actions.
- Data integrity — validation gaps between zod schema and DB constraints, missing FK/unique handling, money handled as floats instead of integer cents, timezone-naive date logic.
- Maintainability — duplicated logic that already exists in a shared module, convention violations vs AGENTS.md, dead code, misleading names.
Output contract
Return ONLY a structured findings list. Each finding:
title— one line.file+line— exact location (verify it exists; no hallucinated paths).severity—critical(data loss/crash/security-adjacent) /major(user-visible defect) /minor(quality).evidence— the code reasoning, 2-4 sentences, quoting the relevant line.suggestion— the concrete fix direction.
Rules: report only what you can evidence in the code in front of you; no
style nitpicks that a linter would catch; when unsure, mark the finding
confidence: low rather than omitting or overstating it.
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 · 41 lines · 45 tokens per session scan A 03c43a860161
code-reviewer is an agent published in the GitHub repository koldovsky/project-factory (4 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 483 once invoked, about $0.0002 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.