code-ultragraph-review

code-ultragraph-review is a skill for Claude Code, Codex from will-pagane/claude-superdev-harness. It costs 0 tokens per session (4,318 once invoked), scanned A, original, MIT.

A read-only whole-codebase review that divides a project into areas and uses multiple reviewers to check them before combining the results. It requires a committed knowledge graph, which is a stored map of the codebase.

In plain words
What is it for?
Use it for an extensive code audit and consolidated findings report, or with autopilot for the documented automated fix pipeline.
Why use it?
It helps review large repositories systematically and reduces duplicate or unverified findings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Codex.

Good fit Use it for an extensive code audit and consolidated findings report, or with autopilot for the documented automated fix pipeline.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/will-pagane/claude-superdev-harness/code-ultragraph-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 will-pagane/claude-superdev-harness --skill code-ultragraph-review
Clone the repo
git clone --depth 1 https://github.com/will-pagane/claude-superdev-harness

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 code-ultragraph-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/will-pagane/claude-superdev-harness/code-ultragraph-review/github.svg)](https://agentmods.dev/skills/will-pagane/claude-superdev-harness/code-ultragraph-review)
Your own site
<a href="https://agentmods.dev/skills/will-pagane/claude-superdev-harness/code-ultragraph-review"><img src="https://agentmods.dev/badge/skills/will-pagane/claude-superdev-harness/code-ultragraph-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 code-ultragraph-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/will-pagane/claude-superdev-harness/code-ultragraph-review"><img src="https://agentmods.dev/badge/skills/will-pagane/claude-superdev-harness/code-ultragraph-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,318 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 $0.00000 $0.04318
Opus 5 $0.00000 $0.02159
Sonnet 5 $0.00000 $0.00864
Haiku 4.5 $0.00000 $0.00432

Measured 8d ago against content hash 75c0d444140d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

code-ultragraph-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 8d ago.

The scan reads SKILL.md. This mod also ships 12 executable files (apply-workflow.js, lib/categories.mjs, lib/categories.test.mjs, …), 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/code-ultragraph-review/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Ultragraph Review

Overview

A deep, whole-codebase review is too large for one context to do well. This skill runs it as a graph-informed, multi-agent ultracode workflow: the committed knowledge graph partitions the codebase and surfaces hotspots; dozens of subagents review slices across every finding class; each finding is adversarially verified before it survives; results are deduped and severity-ranked into one report.

Two hard rules:

  1. No graph → no run. This skill only operates on a project that already has a committed knowledge graph.
  2. Always ultracode. The review MUST run via the Workflow tool. Never do it inline, and never with ad-hoc Agent teammates — defaulting to a handful of inline teammates is the exact failure mode this skill exists to prevent.

Invocation & modes

  • /code-ultragraph-review <category> → read-only review (current behavior). Writes a report, stops.
  • /code-ultragraph-review <category> --autopilot → fully autonomous WRITE pipeline, category-driven by lib/categories.mjs: worktree → runtime signals (skipped when the mission has no signal provider) → deep-dive workflow → report → headless Codex refine → classify → apply (parallel + SDD) → verify+auto-repair → Pull Request. NO human gates. Opt-in only; without --autopilot the skill never writes.
  • Supported missions (the <category> arg): performance, security, correctness, cleanup, code-health. Each is one entry in lib/categories.mjs (includeCategories, signals, branchPrefix, prTitlePrefix). Adding a mission = adding one registry entry. Default <category> is performance.

Resolve <category> (default performance) and the --autopilot flag from the skill args first. Record the skill's base directory (reported on load) — every script below is referenced relative to it as <BASE>.

Activation gate (do this FIRST)

Detect a knowledge graph — look for graphify-out/, .graphify/, or any directory holding both graph.json and GRAPH_REPORT.md:

Read the full file on GitHub · 127 lines

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. 8d ago First seen · 127 lines · 0 tokens per session scan A 75c0d444140d

Subscribe to this mod's changes

code-ultragraph-review is a skill published in the GitHub repository will-pagane/claude-superdev-harness (4 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,318 tokens. 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.

Related

Other skills, from other repositories

sol-luna-router

Route substantial coding or repository-review work through a two-stage Sol commander/verifier and separate Luna Max CLI worker. Use when the user explicitly asks Sol to direct or supervise Luna, explicitly requests this router, needs an isolated auditable Luna-owned implementation with a Sol review loop, or asks to…

majiayu000/spellbook · 123 tokens

idea-team

A structured group discussion for exploring a product idea through three roles: researcher, critic, and analogy finder. The roles look for evidence, weaknesses, and useful comparisons.

majiayu000/spellbook · 182 tokens

codebase-audit

A read-only method for auditing an entire codebase across contracts, data integrity, errors, security, architecture, technical debt, configuration, and caching. It produces prioritized findings and a repair roadmap.

majiayu000/spellbook · 176 tokens

codex-agent

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.

majiayu000/spellbook · 45 tokens

project-health-auditor

Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.

majiayu000/spellbook · 31 tokens

review-gate

Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…

majiayu000/spellbook · 95 tokens