synthesis-pr-review

synthesis-pr-review is a skill for Claude Code, Codex from synthesisengineering/synthesis-skills. It costs 65 tokens per session (4,209 once invoked), scanned A, original, Apache-2.0.

A method for reviewing the changes introduced by a pull request, which is a proposed code change submitted for approval. It is designed for projects that follow the Synthesis engineering workflow.

In plain words
What is it for?
Use it to assess pull requests, investigate the root cause of changes, identify regression risks, and decide whether a change is ready for integration.
Why use it?
It helps reviewers judge whether a change fixes its intended problem without causing regressions or weakening the wider system. The review looks beyond whether the code appears to work.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the synthesis-skills plugin — 63 skills, 4 hooks shipped together

Good fit Use it to assess pull requests, investigate the root cause of changes, identify regression risks, and decide whether a change is ready for integration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synthesisengineering/synthesis-skills/synthesis-pr-review
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.

Any agent
npx skills add synthesisengineering/synthesis-skills --skill synthesis-pr-review
Clone the repo
git clone --depth 1 https://github.com/synthesisengineering/synthesis-skills

Made for: Claude Code, Codex.

Or install synthesis-skills, the plugin that ships this one along with the rest of its 63 skills, 4 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 synthesis-pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-pr-review/github.svg)](https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-pr-review)
Your own site
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-pr-review"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-pr-review/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.

agentmods 80×15 button for synthesis-pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-pr-review"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,209 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Tool Misuse · line 115
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
  • medium Excessive Agency · line 285
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00065 $0.04209
Opus 5 $0.00032 $0.02105
Sonnet 5 $0.00013 $0.00842
Haiku 4.5 $0.00006 $0.00421

Measured 11d ago against content hash f35e298dc149, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

synthesis-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 11d 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/synthesis-pr-review/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesis PR Review

A pull request in a synthesis-coded project is not just "does the code work?" It is "does this change make the system better without making it worse?" This skill defines how to evaluate that.


Where This Fits

Eight related engineering skills cover different scopes and lifecycle phases:

Skill Scope When to use
preplan Architecture-decision locking for a ticket Before any plan exists — lock the load-bearing design choices via Q&A
code-planning Approach selection for a task Before writing code — evaluate alternatives, pick the best approach
implementation-integrity Self-verification of a single implementation After completing work — "Is my code genuinely complete?"
code-audit 10-dimension quality scan of a diff After implementation — systematic quality measurement
preflight Branch readiness gate Before creating a PR — tests, types, audit, commit hygiene
review-triage PR queue prioritization Before starting review — which PR to review next
pr-review (this one) Delta review of a single change Every PR, before peer approval or lead integration
code-integration Integration workflow (adopt-and-adapt pattern, quality gates) When merging contributor work into main
codebase-review Full codebase audit (16 categories, tiered) Periodic health check or major milestone

PR review is the most frequent review skill. It happens on every change. The synthesis-code-audit skill provides systematic quality data that feeds into reviews; this skill provides the judgment-based evaluation and communication. The quality gates from synthesis-code-integration apply here, but this skill operationalizes them as specific review steps.


The Delta Review Mindset

A PR review is a delta review — you are evaluating a change against the current state of the codebase, not evaluating the codebase itself.

Key questions:

Read the full file on GitHub · 346 lines

Files

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.

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. 11d ago First seen · 346 lines · 65 tokens per session scan A f35e298dc149

Subscribe to this mod's changes

synthesis-pr-review is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 4,209 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.