code-review-graph

code-review-graph is a skill for Claude Code from DDS-Solutions/AI-TadPole-OS. It costs 53 tokens per session (668 once invoked), scanned A, original, MIT.

A code-review system that maps how files and program elements depend on one another, then selects the parts affected by a change. An abstract syntax tree is a structured representation of source code.

In plain words
What is it for?
It helps inspect a change’s blast radius, find related code before refactoring, and query structural relationships using a SQLite graph database.
Why use it?
An AI reviewer does not always need to read an entire codebase to assess one change. Dependency mapping focuses the review on the likely impact area and can reduce the amount of text processed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/dds-solutions/ai-tadpole-os/code-review-graph
Any agent
npx skills add DDS-Solutions/AI-TadPole-OS --skill code-review-graph
Clone the repo
git clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OS

Made for: Claude Code.

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-review-graph

README.md
[![agentmods](https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/code-review-graph.svg)](https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/code-review-graph)
Your own site
<a href="https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/code-review-graph"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/code-review-graph.svg" alt="Measured on agentmods" 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 668 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 5.1 $0.00053 $0.00668
Opus 5 $0.00026 $0.00334
Sonnet 5 $0.00011 $0.00134
Haiku 4.5 $0.00005 $0.00067

Measured 6d ago against content hash a811cc0d7474, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

code-review-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 6d 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.

.agent/skills/code-review-graph/SKILL.md · 65 lines

What it actually says

[!IMPORTANT] AI Context & Knowledge Heritage

  • Subsystem: Agent Skills Registry / code-review-graph
  • Architecture: @docs ARCHITECTURE:Documentation
  • Failure Path: Information drift, legacy terminology, or documentation mismatch.
  • Observability: Traceability via execution/parity_guard.py ([SKILL])

Code Review Graph (AST Blast Radius Protocol)

Purpose: Reduce AI token consumption by up to 49x by loading precise structural AST dependency slices instead of reading entire folders.


🎯 Progressive Disclosure & L3 Reference Index

Read REQUIRED core logic below; consult deep L3 Reference Guides on demand:

L3 Reference Guide Purpose Trigger / When to Load
references/graph_cli_and_benchmarks.md External MCP configuration, token reduction benchmarks, SQLite schema External repo setup & MCP server config

1. Native Tadpole OS Graph Commands

In this repository, graph intelligence is natively powered by server-rs/src/bin/graph_query.rs:

# 1. Inspect Blast Radius of a file before refactoring (MANDATORY GUARD)
npm run graph:blast:guard -- --path server-rs/src/routes/system.rs

# 2. Look up symbol definition, callers, and callees
npm run graph:lookup -- --name AppState

# 3. Export complete symbol graph to JSON
npm run graph:export

2. Mandatory Pre-Refactor Protocol

Before making non-trivial code modifications across Rust, TypeScript, or Python files:

  1. Query Blast Radius: Run npm run graph:blast:guard -- --path <target_file>.
  2. Ingest Targeted Slice: Review only the returned callers and callees (~1k–3k tokens) instead of reading every directory file.
  3. Verify Constraints: Ensure edits preserve all required call signatures and return types.

3. Decision Matrix: When to Query the Graph

Task Scope:
├── Single Isolated File / Pure Doc ➔ Direct edit (Skip graph)
├── Multi-File / Shared Contract     ➔ Run graph:blast:guard (Mandatory)
└── Unfamiliar Function Symbol       ➔ Run graph:lookup (Instant caller mapping)
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. 6d ago First seen · 65 lines · 53 tokens per session scan A a811cc0d7474

Subscribe to this mod's changes

code-review-graph is a skill published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 668 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

server-side-calls

Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.

trpc/trpc · 61 tokens

migrate-oxlint

Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.

oxc-project/oxc · 44 tokens

axum-test-transport

Choose between in-process tower::ServiceExt::oneshot tests and real tokio::net::TcpListener server tests for Axum services in this repository.

fastrepl/anarlog · 41 tokens

changeset-pr

Create or update a .changeset/.md file for the current branch or PR in this repository, choose the correct package scope and release type, and verify the result against repo-specific Changesets config. Use when a publishable package changed, when a PR is missing a changeset, when an existing changeset needs…

module-federation/core · 88 tokens

gh-pr-metadata

Update the current GitHub PR title and body for this repository so they match the repo's pull request template and conventional-commit title style. Use when a PR title is vague or misformatted, when the PR body is missing required sections or checklist items, when Codex needs to normalize PR metadata before review or…

module-federation/core · 86 tokens

beui-pro

Choose, inspect, install, and compose licensed beUI Pro premium React blocks from the authenticated shadcn registry. Use when building or improving landing pages with beUI Pro, installing @beui-pro items, selecting premium heroes, features, pricing, social proof, CTAs, navigation, footers, or other page sections, or…

starc007/ui-components · 83 tokens