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 commands/ivanlutsenko/awac-ai-agent-plugins/reviewgit clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-pluginsWrote 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/commands/ivanlutsenko/awac-ai-agent-plugins/review)<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/review"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/review.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.03762 |
| Opus 5 | $0.00014 | $0.01881 |
| Sonnet 5 | $0.00006 | $0.00752 |
| Haiku 4.5 | $0.00003 | $0.00376 |
Grade C, and why
review scanned grade C with 2 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 3d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://cli.coderabbit.ai/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(gh:*), Bash(glab:*), Bash(git:*), Bash(coderabbit:*), Bash(cr:*), Bash(curl:*), Bash(python3:*), Bash(which:*), Bash(wc:*), Bash(head:*), Bash(tail:*), Bash(cat:*), Bash(find:*), Bash(grep:*), Bash(rg How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Combined Code Review
Context
- Directory: !
pwd - Branch: !
git branch --show-current 2>/dev/null || echo "detached HEAD" - Has changes: !
git status --porcelain 2>/dev/null | head -1 | grep -q . && echo "yes" || echo "no"
Step 0 — Read config
Check if config exists at .claude/combined-review.local.md. If it exists, read the language setting from YAML frontmatter.
If config doesn't exist, use default: language: system.
Language resolution:
system→ detect from CLAUDE.md (look for language hints like "Отвечай", "русский", etc.) or fall back to Englishen/ru/uk→ use directly
Apply the resolved language to the final report output (Step 6). Agents work internally in English for accuracy; only the final report is translated.
Arguments
$ARGUMENTS
Finding format
CRITICAL: every finding MUST include file path and line number: path/to/File.kt:42.
Step 1 — Parse arguments
Split $ARGUMENTS into mode and options:
Mode (first argument or pair):
- Empty → current changes (uncommitted + staged)
--base <branch>→ current branch vs specified- Number (
123) → PR/MR number. Detect the forge fromgit remote get-url origin:- host contains
github→ GitHub PR (usegh) - host contains
gitlab→ GitLab MR (useglab)
- host contains
!123or a.../-/merge_requests/123URL → GitLab MR explicitly (useglab, repo = the MR's project)- Two branch-like arguments → diff of first relative to second (target is second)
feature/X feature/Yfeature/X to feature/Yfeature/X...feature/Y
Branch-like: contains /, or starts with feature/, fix/, release/, hotfix/, master, main, develop.
!Nis zsh-escaped as\!Nwhen typed — the literal mode value is!N. Ifgh/glabreturns 404 for a bare number, you likely picked the wrong forge — re-check the origin host.
Options (after mode):
+comments— add comment analysis+types— add type design analysis+simplify— add code simplification+threads— after the report, post findings as inline resolvable threads on the MR/PR (GitLab MR only; see Step 7). Opt-in — never post without this flag or an explicit request.all— run all agents including optional
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.
- 3d ago First seen · 332 lines · 28 tokens per session scan C 38935f8bb0ad
review is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 3,762 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.