github-pr-comment

github-pr-comment is a skill for Claude Code, Codex from runxhq/runx. It costs 38 tokens per session (703 once invoked), scanned A, original, Apache-2.0.

A narrowly scoped tool for posting one exact comment on a known GitHub pull request and checking that the comment was created.

In plain words
What is it for?
Use it after a code review has produced final wording and you need to publish that single comment safely.
Why use it?
It prevents comments from being posted to the wrong repository or pull request, and catches uncertain or duplicate results through readback.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/runxhq/runx/github-pr-comment
Any agent
npx skills add runxhq/runx --skill github-pr-comment
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

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 github-pr-comment

README.md
[![agentmods](https://agentmods.dev/badge/skills/runxhq/runx/github-pr-comment.svg)](https://agentmods.dev/skills/runxhq/runx/github-pr-comment)
Your own site
<a href="https://agentmods.dev/skills/runxhq/runx/github-pr-comment"><img src="https://agentmods.dev/badge/skills/runxhq/runx/github-pr-comment.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 703 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 $0.00038 $0.00703
Opus 5 $0.00019 $0.00351
Sonnet 5 $0.00008 $0.00141
Haiku 4.5 $0.00004 $0.00070

Measured 2d ago against content hash c9c0ce9bca47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

github-pr-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 2d 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.

skills/github-pr-comment/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub PR Comment

Post one bounded review comment to one known GitHub pull request. The skill is deliberately narrower than a general GitHub operator: it binds the exact repository, pull request, and comment body to a scoped provider operation, and closes only when provider evidence identifies and reads back the created note.

Use it after a review workflow has produced final wording and the operator wants that exact note posted. Use issue-triage for analysis and drafting, and a broader GitHub skill for other resource types. This skill never merges a pull request; comment authority cannot be promoted into merge authority.

Composes

  • github-mcp-merge-pr#default
  • github-mcp-pr-review-note#default

How it works

  1. Supply owner/name, the exact pull-request number, exact comment body, and a stable idempotency key for that body.
  2. The default post runner computes the body digest and admits the write only under a compatible pr.comment grant.
  3. Native provider.mutate posts under pr.comment; native provider.read then reads the returned comment ref under pr.read. Repository, PR number, comment ref, and body digest must match before completion.
  4. The explicit comment runner preserves the separately human-gated bundled examples/github-mcp-hero/review-note path as the canonical MCP composition and deterministic harness surface. It is not live Connect evidence.

The separate merge-refused runner routes the same comment grant to the bundled examples/github-mcp-hero/merge-pr denial fixture. It is an executable authority test: a pr.merge request must seal as policy denied, never as a backdoor merge path.

Stop conditions

  • Stop when repository, pull-request number, body, or idempotency key is missing or changes after admission.
  • The explicit comment runner stops when its human approval is absent or denied; the default post runner does not add that second gate.
  • Refuse a provider grant that does not resolve uniquely to pr.comment.
  • Refuse a missing, ambiguous, wrong-provider, or under-scoped GitHub binding; compatible local gh, hosted connectors, and MCP transports all remain behind the same provider effect rather than a raw token or package HTTP client.
  • Do not treat mutation acceptance without an independent comment read, stable comment ref, and matching body digest as final readback.
  • Never merge, close, label, or otherwise mutate the pull request beyond the exact comment.

Read the full file on GitHub · 67 lines

Files

What ships with it

3 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. 2d ago First seen · 67 lines · 38 tokens per session scan A c9c0ce9bca47

Subscribe to this mod's changes

github-pr-comment is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed 3d ago), licensed Apache-2.0. It adds 38 tokens to every session and 703 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 2026-09-03.