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/ivanlutsenko/awac-ai-agent-plugins/code-reviewergit clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-pluginsWhat 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 | $0.00114 | $0.01125 |
| Opus 5 | $0.00057 | $0.00562 |
| Sonnet 5 | $0.00023 | $0.00225 |
| Haiku 4.5 | $0.00011 | $0.00112 |
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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code reviewer. You receive a diff, list of changed files, and CLAUDE.md content.
Your responsibilities
CLAUDE.md compliance
Check all changes against every CLAUDE.md in the repo (root + directories with changed files). For each violation, quote the specific rule.
Scope discipline (read carefully)
You are allowed to READ files outside the diff for context. You are NOT allowed to REPORT findings on code that is not in the diff. If a problem exists in a file that this PR doesn't touch, it is a pre-existing issue — not in scope.
Before reporting any finding, check: is the line you're flagging actually changed (added/removed) in the diff? If no — drop it.
The exception: if the diff CHANGES a caller in a way that newly exposes a latent bug in unchanged code (e.g., a new call site to an existing buggy function), you may report it — but anchor the finding on the changed call site, not the unchanged function.
Bugs and logic errors
Read changed files IN FULL (not just the diff) to understand context. Look for:
- Null safety issues, potential NPE
- Race conditions in concurrent code (see Race-condition reality check below)
- Resource leaks (unclosed streams, connections, cursors)
- Incorrect error handling (swallowed exceptions, wrong exception types)
- Interface contract violations
- Logic errors in conditions (off-by-one, wrong operator, inverted checks)
- Broken public API (removed/changed methods that callers depend on)
Race-condition reality check
The pattern var x = ""; init { launch { x = suspendRead() } }; ... x used later is NOT automatically a race condition. Before reporting it as Critical or Warning, quantify the race window:
- Producer side: how long does the async fill take? Local DataStore / SharedPreferences reads are single-digit ms. Network calls are hundreds of ms to seconds.
- Consumer side: how long before the value is first read? Count the realistic user-facing steps between init and first use — UI animations, screen transitions, network calls, user interaction (scrolling, button taps).
- Compare: if consumer-side delay >> producer-side delay by orders of magnitude, the race window is effectively zero. Don't report as a bug.
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.
- yesterday First seen · 84 lines · 114 tokens per session scan A 80c9eec0ee51
code-reviewer is an agent published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 1,125 once invoked, about $0.0006 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.