agentmods.dev

pr-review-engine

pr-review-engine is a skill for Claude Code, Codex from morpho-org/sdks. It costs 63 tokens per session (7,955 once invoked), scanned A, original, MIT.

A shared engine that coordinates several code-review checks for pull requests and local changes. It chooses relevant review agents, runs them, and combines their findings.

In plain words
What is it for?
Use it as the internal dispatcher for CI, GitHub, local, and fix-oriented pull-request review commands.
Why use it?
It avoids duplicating review logic across different review commands and gathers multiple perspectives into one result.

Skill for Claude CodeCodex

not rated 40 changed today A scan 63 tokens original MIT
View the source file morpho-org/sdks
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/morpho-org/sdks/pr-review-engine
Any agent
npx skills add morpho-org/sdks --skill pr-review-engine
Clone the repo
git clone --depth 1 https://github.com/morpho-org/sdks

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 pr-review-engine

README.md
[![agentmods](https://agentmods.dev/badge/skills/morpho-org/sdks/pr-review-engine.svg)](https://agentmods.dev/skills/morpho-org/sdks/pr-review-engine)
Your own site
<a href="https://agentmods.dev/skills/morpho-org/sdks/pr-review-engine"><img src="https://agentmods.dev/badge/skills/morpho-org/sdks/pr-review-engine.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,955 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 $0.00063 $0.07955
Opus 5 $0.00032 $0.03978
Sonnet 5 $0.00013 $0.01591
Haiku 4.5 $0.00006 $0.00796

Measured today against content hash d23a8b4fa437, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-review-engine 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.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/build-changed-lines.test.ts, scripts/build-changed-lines.ts, scripts/findings-ledger.test.ts, …), 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.

.agents/pr-review-engine/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-review-engine — shared multi-lens review dispatcher

This file is the shared review engine for the /pr-review-ci, /pr-review-gh, /pr-review-local, and /pr-fix slash commands. It supersedes the previous shared dispatcher at .agents/lib/pr-review-base.md.

Do NOT invoke this file directly. It is consumed by other commands — it is not symlinked into .claude/commands/ and assumes the caller has resolved branches and head SHA in its own Steps 1–2. Callers hand control to this file's Steps 3–6.

The base contract: callers pass these resolved values into Steps 3–6 and consume the deduplicated findings list + <FAILED_AGENTS> count produced by Step 6.

Runtime requirement. The bundled scripts under scripts/ are run as node .agents/pr-review-engine/scripts/<file>.ts and rely on Node's native TypeScript type-stripping (Node ≥ 22.18; the repo's dev/CI runtime is newer). This is a requirement of the review tooling only — it is not the published-package Node floor (engines.node in the root package.json).

Success criteria

How a caller knows the engine is working (rough targets, not hard thresholds):

  • Triggering precision — CI/release-only diffs fire ci-release-security; protocol-surface diffs collect ABI/address context for morpho-protocol and web3-security; agentic-system diffs fire skill-authoring.
  • False-positive ceiling — ≤ 10% of agent findings dropped by the scope filter on a healthy diff. If consistently higher, the diff path normalization or <CHANGED_LINES> build is wrong.
  • 0 failed agents on a clean diff — <FAILED_AGENTS> is empty when every agent's JSON parses and matches the WHAT/FIX schema. If non-zero, check schema injection in Step 5.
  • Bounded cost — a typical review fans out 8 baseline + 0–2 conditional agents.

Inputs (from caller's Steps 1–2)

Caller-provided Source
<OWNER>, <REPO> parsed from git remote
<HEAD_BRANCH> gh pr view → headRefName (PR modes) OR git branch --show-current (Local-only)
<BASE_BRANCH> gh pr view → baseRefName (PR modes) OR --local arg / auto-detected default branch
<HEAD_SHA> gh pr view → headRefOid (PR modes) OR git rev-parse HEAD (Local-only)
<DIFF_SOURCE> pr (use origin/<BASE_BRANCH>...<HEAD_REF>) OR local (use origin/<BASE_BRANCH>...HEAD and overlay uncommitted)
<HEAD_REF> Caller-supplied for <DIFF_SOURCE>=pr (origin/<HEAD_BRANCH>, or origin/pr/<PR_NUMBER> when fetched via refs/pull/<PR_NUMBER>/head — required for fork PRs); HEAD for <DIFF_SOURCE>=local
<EXCLUDE_AGENTS> Optional list of agent names to skip in Step 5 (e.g. ["documentation"] from /pr-review-local --fast). Defaults to empty.
<INTENT_CONTEXT> Optional caller-supplied intent/history block — changed-commit messages, and (when the caller talks to GitHub) the PR title+body. Injected into the Step 5 envelope between items 6 and 7. Empty by default; callers that can't reach the data omit it.

Read the full file on GitHub · 400 lines

Files

What ships with it

27 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 d23a8b4fa437
  2. 3d ago First seen · 400 lines · 63 tokens per session scan A 911101d010bd

Subscribe to this mod's changes

pr-review-engine is a skill published in the GitHub repository morpho-org/sdks (40 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 7,955 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 2026-09-01.

Code reviewanvilapollobundlerethersgraphqlliquidation
Related

Other skills, from other repositories

apollo-router

Version-aware guide for configuring and running Apollo Router for federated GraphQL supergraphs. Generates correct YAML for both Router v1.x and v2.x. Use this skill when: (1) setting up Apollo Router to run a supergraph, (2) configuring routing, headers, or CORS, (3) implementing custom plugins (Rhai scripts or…

apollographql/skills · 140 tokens

apollo-router-plugin-creator

Guide for writing Apollo Router native Rust plugins. Use this skill when: (1) users want to create a new router plugin, (2) users want to add service hooks (routerservice, supergraphservice, executionservice, subgraphservice), (3) users want to modify an existing router plugin, (4) users need to understand router…

apollographql/skills · 116 tokens

apollo-client

Guide for building React applications with Apollo Client 4.x. Use this skill when: (1) setting up Apollo Client in a React project, (2) writing GraphQL queries or mutations with hooks, (3) configuring caching or cache policies, (4) managing local state with reactive variables, (5) troubleshooting Apollo Client errors…

apollographql/skills · 74 tokens

apollo-server

Guide for building GraphQL servers with Apollo Server 5.x. Use this skill when: (1) setting up a new Apollo Server project, (2) writing resolvers or defining GraphQL schemas, (3) implementing authentication or authorization, (4) creating plugins or custom data sources, (5) troubleshooting Apollo Server errors or…

apollographql/skills · 73 tokens

apollo-connectors

Guide for integrating REST APIs into GraphQL supergraphs using Apollo Connectors with @source and @connect directives. Use this skill when the user: (1) mentions "connectors", "Apollo Connectors", or "REST Connector", (2) wants to integrate a REST API into GraphQL, (3) references @source or @connect directives, (4)…

apollographql/skills · 96 tokens

apollo-federation

Guide for authoring Apollo Federation subgraph schemas. Use this skill when: (1) creating new subgraph schemas for a federated supergraph, (2) defining or modifying entities with @key, (3) sharing types/fields across subgraphs with @shareable, (4) working with federation directives (@external, @requires, @provides…

apollographql/skills · 103 tokens