agentmods.dev

review-via-graph

review-via-graph is a skill for Claude Code, Codex from Justinmendezai/The-Adam-Repo. It costs 53 tokens per session (1,578 once invoked), scanned A, original, Apache-2.0.

A structural code-review workflow for a builder agent's branch, using a code-review graph to examine relationships between files, functions, and dependencies. It reviews the change before the branch is merged.

In plain words
What is it for?
Use it after a builder reports a slice as complete and before merging it. It checks changed APIs, their callers and importers, dependency relationships, surrounding code, and slice tests, while requiring precise evidence for findings.
Why use it?
Passing tests does not always reveal dead code, broken callers, layering problems, or dependency cycles. This review looks for those structural failure modes.

Skill for Claude CodeCodex

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

not rated 12repo +1 18d ago A scan 53 tokens original Apache-2.0

Good fit Use it after a builder reports a slice as complete and before merging it. It checks changed APIs, their callers and importers, dependency relationships, surrounding code, and slice tests, while requiring precise evidence for findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/justinmendezai/the-adam-repo/review-via-graph
View source ↗ Justinmendezai/The-Adam-Repo justinmendez.ai
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 Justinmendezai/The-Adam-Repo --skill review-via-graph
Clone the repo
git clone --depth 1 https://github.com/Justinmendezai/The-Adam-Repo

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 review-via-graph

README.md
[![agentmods](https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/review-via-graph/github.svg)](https://agentmods.dev/skills/justinmendezai/the-adam-repo/review-via-graph)
Your own site
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/review-via-graph"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/review-via-graph/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 review-via-graph

Your own site · 80×15
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/review-via-graph"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/review-via-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,578 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 $0.00053 $0.01578
Opus 5 $0.00026 $0.00789
Sonnet 5 $0.00011 $0.00316
Haiku 4.5 $0.00005 $0.00158

Measured 12d ago against content hash be76777cb8b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-via-graph 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 12d 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/review-via-graph/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-via-graph

Token-cheap structural review. Lean on the code-review-graph MCP to find issues a green test suite alone won't catch: dead code, callers of removed/changed APIs, layering violations, dependency cycles, etc.

This is the orchestrator's first review pass. Runtime review (review-runtime) comes after.

Reviewer contract

The failure mode of an LLM reviewer is noise: manufactured findings that train the orchestrator to ignore reviews. Hold every finding to this contract before recording it.

Pre-report gate (all four must be "yes")

  1. Can I cite the exact location? A file:line (or symbol) from the MCP. "Somewhere in the auth layer" is not actionable; drop it.
  2. Can I name the concrete failure mode? The input, state, and bad outcome. If you cannot name the trigger, you are pattern-matching, not reviewing.
  3. Have I checked the surrounding context? Callers, importers, and the slice's tests. Many apparent issues are already guarded one frame up.
  4. Is the severity defensible? A missing doc-comment is never critical. Severity inflation erodes trust faster than a missed nit.

critical findings must include the location, the specific failure scenario, and why existing guards (types, validation, the test suite) do not catch it. If you cannot produce all three, demote to warning or drop.

Skip these (common false positives)

  • "Consider adding error handling" where the caller, framework, or an upstream boundary already handles it.
  • "Missing input validation" on internal functions whose callers already validate (trace one caller first).
  • "Function too long" for exhaustive switches, config objects, or test tables. Length is not complexity.
  • Stylistic preferences that do not violate plan/CONTEXT.md or project rules.
  • Issues in unchanged code outside the slice, unless critical security. Record those in scratch/review-debt.md, not as slice findings.

Zero findings is a valid review

A clean, well-scoped, green slice with no structural issues should return zero findings and verdict approve. Do not manufacture findings to justify the pass.

Read the full file on GitHub · 109 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. 12d ago First seen · 109 lines · 53 tokens per session scan A be76777cb8b0

Subscribe to this mod's changes

review-via-graph is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,578 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens