load-pr-review

load-pr-review is a skill for Claude Code from sd0xdev/sd0x-harness. It costs 77 tokens per session (4,368 once invoked), scanned A, original, MIT.

A tool that loads comments from a GitHub pull request, where proposed code changes are reviewed, into an AI session for analysis and planning. It groups review discussions into separate threads and normally only analyzes them.

In plain words
What is it for?
Use it to review pull-request comments, classify their importance, plan responses or fixes, and optionally write changes back when explicitly enabled.
Why use it?
It turns scattered pull-request feedback into an organized triage report without changing code automatically. This helps decide which comments need action before planning or applying fixes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/run-skill.sh load-pr-review load-pr-review.js \.

Part of the sd0x-dev-flow plugin — 98 skills, 16 agents, 5 hooks shipped together

Good fit Use it to review pull-request comments, classify their importance, plan responses or…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/sd0xdev/sd0x-harness
agentmods
npx agentmods add skills/sd0xdev/sd0x-harness/load-pr-review

Made for: Claude Code.

Or install sd0x-dev-flow, the plugin that ships this one along with the rest of its 98 skills, 16 agents, 5 hooks.

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 load-pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/load-pr-review.svg)](https://agentmods.dev/skills/sd0xdev/sd0x-harness/load-pr-review)
Your own site
<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/load-pr-review"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/load-pr-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00077 $0.04368
Opus 5 $0.00039 $0.02184
Sonnet 5 $0.00015 $0.00874
Haiku 4.5 $0.00008 $0.00437

Measured yesterday against content hash 1ceeccd5dfb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

load-pr-review 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/load-pr-review.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/load-pr-review/SKILL.md · 438 lines

How it starts

The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Load PR Review

Trigger Keywords

load pr review, pr feedback, address review, review comments, pr comments

When NOT to Use

Need Use Instead
Create a code review /codex-review-fast or /codex-review
Post new review comments /pr-comment
Create a PR /create-pr
PR status overview /pr-summary
Investigate code history /git-investigate

Core Principle

Load review → independent per-thread triage → analysis report → user decides next step
Default: analysis-only. Fix and writeback require explicit --mode fix / --writeback.
Data plane (JS script) handles fetch/normalize/writeback.
Control plane (this SKILL.md) handles classification, fix orchestration, auto-loop.

Non-Negotiable Rules

# Rule Violation =
1 Plan/fix mode MUST invoke /seek-verdict via Skill tool per unresolved thread (unless --no-verdict) Report invalid — re-run with verdict
2 Step 3 (Present) is blocked until Step 2 (Verdict Triage) completes Report invalid
3 Each /seek-verdict must use fresh Codex context per thread (no batch) Triage invalid
4 Plan output MUST include Codex Verdict Threads field (non-empty, from Step 2) Report rejected

Analysis-Only Default ⚠️

This skill is an analysis tool by default. It loads PR review comments and produces a triage report. It does NOT auto-fix.

Prohibited Behaviors

❌ Prohibited ✅ Correct
Auto-fixing code after loading PR reviews Present analysis report, wait for user to invoke --mode fix
Editing files in plan mode Only read and classify; no writes
Suggesting "let me fix this" without explicit --mode fix "Use --mode fix to start fixing ACTIONABLE threads."
Skipping triage and jumping to fixes Always complete Step 2 verdict triage before any action
Skipping /seek-verdict and classifying threads with AI judgment alone Invoke /seek-verdict per thread via Skill tool; AI judgment is fallback only for failed calls
Outputting plan table without Codex verdict data when --no-verdict was not passed Complete Step 2 before Step 3

Read the full file on GitHub · 438 lines

Files

What ships with it

5 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. yesterday Changed 1ceeccd5dfb6
  2. 3d ago First seen · 438 lines · 77 tokens per session scan A ac240f976fb4

Subscribe to this mod's changes

load-pr-review is a skill published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 4,368 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

code-review

Two-mode skill: (1) adversarial review — spec compliance + code quality + security, confidence-scored findings with file:line evidence; (2) receiving review — verify-before- agreeing discipline for acting on external/human review feedback.

romiluz13/cc10x · 53 tokens

codebase-hygiene

Two-mode skill: (1) find semantic duplicates — functions doing the same thing under different names, invisible to copy-paste detectors; (2) deepen shallow modules — thin wrappers and pass-through layers that spread complexity. Advisory and read-only; changes route through BUILD with full gates.

romiluz13/cc10x · 67 tokens

evaluator-review-contract

Internal Auto-Harness evaluator skill for sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.

redker56/auto-harness · 30 tokens

comet-verify

Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.

rpamis/comet · 32 tokens

comet-review

A read-only review guide for checking the current Comet change, a managed software-change workflow. It focuses on correctness, security, and boundary problems without changing files or advancing the workflow.

rpamis/comet · 30 tokens

comet-github-pr-review

A read-only review process for pull requests in Comet's GitHub repositories. A pull request is a proposed code change; the review checks its current code, related issue, comments, merge status, and automated checks.

rpamis/comet · 69 tokens