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.
npx agentmods add skills/brain-bootstrap/claude-code-brain-bootstrap/code-review-graphnpx skills add brain-bootstrap/claude-code-brain-bootstrap --skill code-review-graphgit clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrapWhat 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.
| Model | Per session | Once 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 |
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.
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
build_graph_tool(repo_path=".")— first run only (or after major refactor)detect_changes_tool(base_branch="main")— risk score + blast radius- If risk score ≥ 60 →
get_dependency_chain_toolon the highest-risk node - If impacted flows present → review them with
get_neighbors_tool - 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.
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.
- 2d ago First seen · 78 lines · 63 tokens per session scan A afb8dbc2cd8c
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.
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…
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.
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.
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.
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.
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/.