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 skills add itechmeat/llm-code --skill coderabbitgit clone --depth 1 https://github.com/itechmeat/llm-codeWrote 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/skills/itechmeat/llm-code/coderabbit)<a href="https://agentmods.dev/skills/itechmeat/llm-code/coderabbit"><img src="https://agentmods.dev/badge/skills/itechmeat/llm-code/coderabbit/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/skills/itechmeat/llm-code/coderabbit"><img src="https://agentmods.dev/badge/skills/itechmeat/llm-code/coderabbit.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 | $0.00074 | $0.02899 |
| Opus 5.5 | $0.00030 | $0.01160 |
| Sonnet 5.5 | $0.00015 | $0.00580 |
| Haiku 4.5 | $0.00007 | $0.00290 |
Grade C, and why
coderabbit 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 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.
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.
which coderabbit || echo "MISSING: install with: 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.
which coderabbit || echo "MISSING: install with: curl -fsSL https://cli.coderabbit.ai/install.sh | sh" How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeRabbit
AI-powered code review for pull requests and local changes.
Quick Navigation
| Task | Reference |
|---|---|
| Install & run CLI | cli-usage.md |
| Configure .coderabbit.yaml | configuration.md |
| Supported tools (40+ linters) | tools.md |
| Git platform setup | platforms.md |
| PR commands (@coderabbitai) | pr-commands.md |
| Claude/Cursor/Codex workflow | agent-integration.md |
| Triage findings | triage.md |
| Fix single issue | fix.md |
| Reporting & metrics | end-to-end-workflow.md |
| End-to-end workflow | end-to-end-workflow.md |
| Windows/WSL setup | windows-wsl.md |
Prerequisites Check (MUST RUN BEFORE REVIEW)
Before running CodeRabbit CLI, verify ALL of the following:
# 1. CLI installed?
which coderabbit || echo "MISSING: install with: curl -fsSL https://cli.coderabbit.ai/install.sh | sh"
# 2. Authenticated?
coderabbit auth status 2>&1 | grep -q "Logged in" || echo "MISSING: run coderabbit auth login"
# 3. Git repo has at least one commit? (CRITICAL — CLI crashes with GitError on empty repos)
git rev-parse HEAD >/dev/null 2>&1 || echo "MISSING: repo has no commits — make at least one commit first"
# 4. Base branch exists? (CLI defaults to 'main')
git rev-parse main >/dev/null 2>&1 || echo "WARNING: 'main' branch not found — use --base <branch>"
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/agent-prompts.md 2.4 KB
- assets/coderabbit.full.yaml 2.8 KB
- assets/coderabbit.minimal.yaml 264 B
- references/agent-integration.md 5.4 KB
- references/cli-usage.md 5.4 KB
- references/configuration.md 6.8 KB
- references/end-to-end-workflow.md 4.3 KB
- references/fix.md 1.7 KB
- references/platforms.md 2.7 KB
- references/pr-commands.md 2.7 KB
- references/tools.md 6.4 KB
- references/triage.md 2.2 KB
- references/windows-wsl.md 962 B
- scripts/run_coderabbit.py 5.9 KB runs code
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 · 290 lines · 74 tokens per session scan C 148e7c1c68ac
coderabbit is a skill published in the GitHub repository itechmeat/llm-code (24 stars, last pushed 24d ago), licensed MIT. It adds 74 tokens to every session and 2,899 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…