Borrowing it
Nothing to install: this file belongs to go-to-k/cdkd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/go-to-k/cdkd/main/.claude/skills/review-pr/SKILL.mdgit clone --depth 1 https://github.com/go-to-k/cdkdWrote 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/go-to-k/cdkd/review-pr)<a href="https://agentmods.dev/skills/go-to-k/cdkd/review-pr"><img src="https://agentmods.dev/badge/skills/go-to-k/cdkd/review-pr/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/go-to-k/cdkd/review-pr"><img src="https://agentmods.dev/badge/skills/go-to-k/cdkd/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.06104 |
| Opus 5 | $0.00024 | $0.03052 |
| Sonnet 5 | $0.00010 | $0.01221 |
| Haiku 4.5 | $0.00005 | $0.00610 |
Grade A, and why
review-pr 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 today.
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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Recommendation
Decide how much review rigor a PR warrants and surface the dispatch prompts. The tiers say what a PR needs AT MINIMUM.
The recommended tier is a FLOOR, not a cap, and wall-clock / token cost is never a reason to come in under it or to stop at it (CLAUDE.md → "Cost is not a tiebreaker"): when unsure which tier applies, take the higher one. Reviewers are read-only agents that run in parallel.
The skill itself never spawns reviewers — it reads PR stats, applies the
heuristic, and prints a recommendation; the main session orchestrator
issues the Agent calls.
Steps
-
A PUSH is not a round-completion signal — a REPLY is. Check for one before opening a round on a head you have not reviewed.
Decide it from WHOSE TURN IT IS, never from a push timestamp. A round is a conversation turn: your comment ends yours, the author's ends theirs. Two push-timestamp spellings were tried and both skip the wait SILENTLY — a
committedtimeline event carries the COMMIT date, not the push time (and that is the ordinary non-force-push shape, so the error is the common case), and an empty$PUSHmakes jq's.created_at > ""true for every comment ever written, which reads as "they replied". Neither errors.PR=<N>; REPO=go-to-k/cdkd ME=$(gh api user -q .login) THEM=$(gh pr view "$PR" --repo "$REPO" --json author -q .author.login) # All three surfaces: issue comments, review BODIES, and review-thread # replies. A contributor answering from "Files changed" -- GitHub's default # -- writes only the last two, and `issues/<N>/comments` never shows them. said() { # said <login> -> newest ISO timestamp, or empty { gh api "repos/$REPO/issues/$PR/comments" --paginate -q ".[]|select(.user.login==\"$1\")|.created_at" gh api "repos/$REPO/pulls/$PR/comments" --paginate -q ".[]|select(.user.login==\"$1\")|.created_at" gh api "repos/$REPO/pulls/$PR/reviews" --paginate -q ".[]|select(.user.login==\"$1\" and .submitted_at!=null)|.submitted_at" } | sort | tail -1 } MINE=$(said "$ME"); THEIRS=$(said "$THEM")
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.
- today Changed · +83 lines 4c0a3ba4f4f4
- yesterday Changed 8d1e1591a9ee
- 4d ago Changed · +80 lines f954f5764d5e
- 5d ago Changed · +21 lines ae642f14276d
- 6d ago Changed · -20 lines 360fe1eda10f
- 10d ago First seen · 279 lines · 49 tokens per session scan A e705ba3ce5df
review-pr is a skill published in the GitHub repository go-to-k/cdkd (138 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 6,104 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 2026-08-30.
Other skills, from other repositories
aws-cdk-mcp-server-mcp
AWS Cloud Development Kit (CDK) best practices, infrastructure as code patterns, and security compliance with CDK Nag.
prowler-compliance-review
Reviews Pull Requests that add or modify compliance frameworks. Trigger: When reviewing PRs with compliance framework changes, CIS/NIST/PCI-DSS additions, or compliance JSON files.
prowler-pr
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml…
agent-squad-python
Use when building or modifying a Python app that uses the agent-squad Python package — async multi-agent orchestration for Python 3.11+: orchestrator, agents (BedrockLLMAgent, AnthropicAgent, OpenAIAgent, SupervisorAgent, GroundedAgent, ChainAgent, and more), classifier routing (Bedrock, Anthropic, OpenAI), storage…
agent-squad-swift
Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widgets, on-device storage, tracing, and…
agent-squad-typescript
Use when building or modifying a Node.js / TypeScript app that uses the agent-squad npm package — multi-agent orchestration: orchestrator, agents (all built-in types + GroundedAgent), classifier routing (Bedrock / Anthropic / OpenAI), storage (in-memory / DynamoDB / SQL), retrievers (Amazon KB / Dakera), and tools…