code-review-graph

A code-change analysis skill that compares Git differences with a base branch and maps affected source code. It reports a risk score, dependent code, signature changes, and affected execution paths.

In plain words
What is it for?
Use it to review changes against main, inspect their blast radius, identify breaking changes, and assess whether they are safe to merge.
Why use it?
It shows what a change may break before a pull request or merge, including effects beyond the edited files.

Skill for Claude CodeCodex

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/brain-bootstrap/claude-code-brain-bootstrap/code-review-graph
Any agent
npx skills add brain-bootstrap/claude-code-brain-bootstrap --skill code-review-graph
Clone the repo
git clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrap

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,016 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 $0.01016
Opus 5 $0.00032 $0.00508
Sonnet 5 $0.00013 $0.00203
Haiku 4.5 $0.00006 $0.00102

Measured 2d ago against content hash afb8dbc2cd8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

.claude/skills/code-review-graph/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-review-graph — Change Risk Analysis

Structural change safety gate. Builds a SHA-256 AST graph from source code, then on any diff computes:

  • Risk score (0–100)
  • Blast radius — all transitively affected nodes (BFS, 100% recall)
  • Breaking changes — nodes whose signature changed
  • Impacted flows — execution paths traversing changed nodes

Quick Decision Matrix

Question Tool
Is this change safe to ship? mcp__code-review-graph__detect_changes_tool(base_branch="main")
Build/rebuild the graph mcp__code-review-graph__build_graph_tool(repo_path=".")
Graph status + stats mcp__code-review-graph__get_graph_info_tool
What changed vs main? mcp__code-review-graph__get_diff_tool(base_branch="main")
Node details mcp__code-review-graph__get_node_tool(node_id="<id>")
Node neighbors mcp__code-review-graph__get_neighbors_tool(node_id="<id>", depth=2)
Find by name mcp__code-review-graph__search_nodes_tool(query="AuthService")
Community structure mcp__code-review-graph__get_communities_tool
Critical path mcp__code-review-graph__get_critical_path_tool(source="<id>", target="<id>")
Dependency chain mcp__code-review-graph__get_dependency_chain_tool(node_id="<id>")

Mandatory Pre-PR Workflow

  1. build_graph_tool(repo_path=".") — first run only (or after major refactor)
  2. detect_changes_tool(base_branch="main") — risk score + blast radius
  3. If risk score ≥ 60 → get_dependency_chain_tool on the highest-risk node
  4. If impacted flows present → review them with get_neighbors_tool
  5. Fix or document risks before merging

Risk Score Interpretation

Score Meaning Action
0–25 Low risk Review and ship
26–50 Moderate Verify blast radius manually
51–75 High Write tests for affected nodes
76–100 Critical Full review + stakeholder sign-off

Lifecycle

First build: build_graph_tool(repo_path=".") — ~6s for 500 files, ~30s for large repos.

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 63 tokens per session scan A afb8dbc2cd8c

Subscribe to this mod's changes

code-review-graph is a skill published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 1,016 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.

Related

Other skills, from other repositories

implement

TRIGGER when: user asks to implement, fix, build, or work on something — whether from a docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Examples: "work on task 1", "fix this bug", "implement feature X from the issue". Provides structured execution with profile detection, dependency…

serpro69/claude-toolbox · 79 tokens

review-spec

Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.

serpro69/claude-toolbox · 44 tokens

chain-of-verification

Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.

serpro69/claude-toolbox · 41 tokens

review-code

Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.

serpro69/claude-toolbox · 37 tokens

review-design

Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.

serpro69/claude-toolbox · 37 tokens

design

Use in pre-implementation (idea-to-design) stages to understand spec/requirements and create a correct implementation plan before writing actual code. Turns ideas into a fully-formed PRD/design/specification and implementation-plan. Creates design docs and task lists in docs/wip/.

serpro69/claude-toolbox · 56 tokens