create-review-comment

create-review-comment is a skill for Claude Code, Codex from i9wa4/dotfiles. It costs 64 tokens per session (384 once invoked), scanned A, original, MIT.

A workflow for drafting Japanese GitHub pull-request review comments after identifying the target change and gathering its context.

In plain words
What is it for?
Use it to infer a pull request, run the relevant checks, prepare a substantive Japanese review, and show the draft without posting it automatically.
Why use it?
It separates review writing from actually posting to GitHub, so comments can be checked and approved before publication.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; $skill-name invocation.

Install

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.

agentmods
npx agentmods add skills/i9wa4/dotfiles/create-review-comment
Any agent
npx skills add i9wa4/dotfiles --skill create-review-comment
Clone the repo
git clone --depth 1 https://github.com/i9wa4/dotfiles

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for create-review-comment

README.md
[![agentmods](https://agentmods.dev/badge/skills/i9wa4/dotfiles/create-review-comment.svg)](https://agentmods.dev/skills/i9wa4/dotfiles/create-review-comment)
Your own site
<a href="https://agentmods.dev/skills/i9wa4/dotfiles/create-review-comment"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/create-review-comment.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 384 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.00384
Opus 5 $0.00032 $0.00192
Sonnet 5 $0.00013 $0.00077
Haiku 4.5 $0.00006 $0.00038

Measured today against content hash c987b98420dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-review-comment 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.

skills/create-review-comment/SKILL.md · 40 lines

What it actually says

Create Review Comment

User-facing trigger for drafting Japanese GitHub PR review comments. $create-review-comment, $create-review-comment #123, and ai-create-review-comment for this branch all start target inference and drafting.

Owns target inference, Japanese draft output, and the no-post-without-approval gate. Review procedure belongs to subagent-review; GitHub mechanics and path hygiene belong to dev-platform-workflow. In tmux-a2a-postman, orchestrator/worker only infer targets and collect PR context before routing substantive review to guardian.

1. Workflow

  1. Infer the target PR from the prompt, current branch, or GitHub context. If missing or ambiguous, ask only for the minimum target identifier.
  2. Read Workflow before changing behavior or giving detailed instructions.
  3. For substantive drafting, use subagent-review through postman: send the review package to guardian, let guardian request critic, and never launch reviewer subagents from orchestrator/worker. Do not ask the user for review mechanics.
  4. Run the checks named in the workflow guide or the nearest repo harness.
  5. Output draft comments visibly for user approval. Do not post them unless the user explicitly asks.

2. References

Files

What ships with it

4 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.

Changes

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.

  1. today Changed c987b98420dc
  2. 6d ago First seen · 40 lines · 64 tokens per session scan A 97eaff9bffb3

Subscribe to this mod's changes

create-review-comment is a skill published in the GitHub repository i9wa4/dotfiles (11 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 384 once invoked, about $0.0003 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.