Borrowing it
Nothing to install: this file belongs to y-hirakaw/mcp-gh-pr-mini. 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/y-hirakaw/mcp-gh-pr-mini/main/.claude/skills/gh-pr-review-comment/SKILL.mdgit clone --depth 1 https://github.com/y-hirakaw/mcp-gh-pr-miniWrote 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/y-hirakaw/mcp-gh-pr-mini/gh-pr-review-comment)<a href="https://agentmods.dev/skills/y-hirakaw/mcp-gh-pr-mini/gh-pr-review-comment"><img src="https://agentmods.dev/badge/skills/y-hirakaw/mcp-gh-pr-mini/gh-pr-review-comment/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/y-hirakaw/mcp-gh-pr-mini/gh-pr-review-comment"><img src="https://agentmods.dev/badge/skills/y-hirakaw/mcp-gh-pr-mini/gh-pr-review-comment.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 | $0.00035 | $0.00799 |
| Opus 5 | $0.00017 | $0.00400 |
| Sonnet 5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
gh-pr-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 12d 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gh-pr-review-comment
Add a review comment to a specific line in a GitHub pull request diff. The comment is automatically prefixed with an AI identifier. Prefer --line (the actual file line number) over the deprecated --position (an offset within the diff) - --position requires re-counting diff hunks and is error-prone.
Command
python3 .claude/skills/gh-pr-review-comment/scripts/add_review_comment.py --owner OWNER --repo REPO --pr-number PR_NUMBER --body "COMMENT" --path FILE_PATH --line LINE
Arguments
| Argument | Required | Description |
|---|---|---|
--owner |
Yes | Repository owner (username or organization) |
--repo |
Yes | Repository name |
--pr-number |
Yes | Pull request number |
--body |
Yes | Comment content (will be prefixed with "[AI] Generated using MCP") |
--path |
Yes | Relative path to the file being commented on |
--line |
One of --line/--position (unless --subject-type file) |
File line number to comment on (preferred) |
--side |
No | Which side of the diff --line refers to: LEFT (old) or RIGHT (new). Default: RIGHT |
--start-line |
No | First line of a multi-line comment range (used together with --line as the last line) |
--start-side |
No | Which side of the diff --start-line refers to. Default: same as --side |
--subject-type |
No | Set to file for a file-level comment when the target line falls outside the diff hunk (omits line/position) |
--position |
One of --line/--position (unless --subject-type file) |
[Deprecated] Position in the diff where the comment should be placed (use gh-pr-changes skill to find valid positions) |
--line and --position are mutually exclusive.
Examples
Add a review comment on a specific file line (preferred):
python3 .claude/skills/gh-pr-review-comment/scripts/add_review_comment.py --owner octocat --repo hello-world --pr-number 42 --body "Consider using a constant here instead of a magic number." --path src/utils.ts --line 124
What ships with it
1 file 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.
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.
- 12d ago First seen · 56 lines · 35 tokens per session scan A 30293290c86c
gh-pr-review-comment is a skill published in the GitHub repository y-hirakaw/mcp-gh-pr-mini (0 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 799 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…