grafel-aware-review
Teaches an AI agent to use grafel MCP tools as a structural second pair of eyes during code review.
Skill by cajasmota
Chalk Labs
Need help deploying grafel-aware-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cajasmota-grafel-aware-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/grafel-aware-review
What's inside
- Skill name
grafel-aware-review- Description
- Teaches an AI agent to use grafel MCP tools as a structural second pair of eyes during code review. Covers impact radius analysis, orphan detection, dead-end flow discovery, cross-repo consistency checks, and pattern violation spotting — with a per-change-type tool sequence, a severity rubric, and worked examples.
- License
- MIT
- Instructions
- 619 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- body: 619 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# grafel-aware-review A structural review protocol for AI agents. This skill turns grafel MCP into a systematic second opinion on every PR — one that catches impact leakage, broken call chains, and pattern drift that diff-only review misses. Prerequisite: the `/using-grafel` skill. This skill assumes you already know the 22 MCP tools and the orientation workflow. --- ## 1. Should I run grafel on this PR? ### Yes — run the structural checks when the diff touches: | Change type | Key risk grafel catches | |-------------|----------------------------| | New/renamed function or method | Callers in other modules still expect the old signature | | Deleted function or method | Orphan call-sites remain in any repo of the group | | New HTTP endpoint | No client calls it yet (dead definition); or it clashes with an existing route | | Changed HTTP endpoint path/method | Existing client calls become orphan callers | | New inter-module import | Introduces an unexpected cluster coupling or a cycle | | New message publish/subscribe | No subscriber (dead publish) or no publisher (dead subscriber) | | Cross-repo call site added | Target entity may not exist in the other repo's graph | | Pattern implementation (new handler, new serializer, etc.) | Does not follow the established structural pattern | ### No — skip grafel when the diff is limited to: - Whitespace, formatting, or lint fixes. - Comment or docstring edits. - Test fixture data files (JSON, YAML, CSV). - Changes that are entirely within a single private function with no exported signature. - Config-only changes (`*.env`, `*.yaml`, `*.toml`) with no code entry points. - Pure CSS/markup with no JS/TS wiring changes. **Quick self-check:** if the change cannot be reached from any entity in the grafel graph (no exported name, no route, no published event), skip the structural pass and review the diff purely on its own terms. --- ## 2. Quick win — one call for 80 % of insights When time is short, a single call surfaces most structural risk: ``` grafel_impact_radius( target="<the changed entity>", scope="entity" ) ``` This call returns: - The blast radius of the change — directly and transitively affected entities. - Whether any affected entities live in a different repo (cross-repo risk). - The PageRank weight of the changed entity (high = high blast radius). If the entity is not found, it is either brand-new (check for orphan callers of the new name) or the repo has not been re-indexed since the PR was opened. **Estimated cost:** ~100–300 tokens. Run this first. If the result is clean and the entity has low PageRank, you may not need the full per-change-type sequence below. --- ## 3. Per-change-type MCP tool sequence ### 3.1 Function / method signature change **Risk:** callers in other modules or repos still call the old signature, or assume a return type that no longer exists. ``` # Step 1: Find the entity and all depth-2 callers grafel_related(entity="<FunctionName>", direction="callers") # Step 2: Inspect for PageRank (blast-radius indicator) grafel_inspect(entity="<FunctionName>") # Step 3: For each top caller — does its call site match the new signature? grafel_get_source(entity="<CallerEntityId>", context_lines=20) # Step 4: Check cross-repo callers grafel_related(entity="<FunctionName>", direction="callers") # Look for entries where entity_id prefix differs from current repo slug ``` **Review comment trigger:** any caller found at depth 1 or 2 that is in a different file or repo — confirm the call site is updated or explicitly listed as a follow-up ticket. --- ### 3.2 Deleted function or method **Risk:** call-sites anywhere in the group still reference the deleted name, creating dead code (orphan callers). ``` # Step 1: Find all callers before deletion is confirmed as safe grafel_related(entity="<DeletedFunctionName>", direction="callers") # If callers is empty: the entity was already absent from the index — safe. # If callers exist: call-sites remain. # Step 2: Expand to enumerate every direct caller grafel_related(entity="<DeletedFunctionName>", direction="callers") # Step 3: Source-read each caller to verify it is also removed in this PR grafel_get_source(entity="<CallerId>", context_lines=15) ``` **Review comment trigger:** any caller not removed in the same PR. Block if caller is in a different repo (cross-repo breakage). --- ### 3.3 New HTTP endpoint
From cajasmota/grafel, MIT.
More from cajasmota/grafel
- 0.607score
grafel-feedback
cajasmota
Generate a privacy-preserving anonymized quality report for sharing with grafel maintainers, then layer an agent-driven "Findings & Interpretation" section on…
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
grafel-tech-docs
cajasmota
Generate the per-repo and group-level technical documentation set — overview, modules, reference, cross-cutting, group synthesis, cross-links, and patterns.
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
grafel-security-audit
cajasmota
Two-phase security audit of the indexed group.
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
grafel-business-docs
cajasmota
Generate group-synthesised, PM-facing documentation — product capabilities, business domain glossary, user journeys as plain-language narratives, business…
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
grafel-graph-quality
cajasmota
Continuous health check of the grafel knowledge graph.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
grafel-test-page
cajasmota
Test the grafel docgen LLM-mode loop end-to-end on a single entity.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
grafel-resolve
cajasmota
Surface and resolve residual edges — runtime dispatch, dynamic URLs, ambiguous bindings — so the graph is fit-for-purpose before any downstream skill consumes…
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
grafel-consult
cajasmota
Hire a specialist consultant (architect, security-auditor, business-analyst, performance-reviewer, refactor-critic, api-designer, data-engineer, qa-reviewer)…
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
grafel-graph-enrich
cajasmota
Annotate the graph with structured YAML frontmatter on http_endpoint, process_flow, and message_topic entities so the dashboard panels (Paths, Flows…
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
using-grafel
cajasmota
Teaches an AI agent how to use grafel MCP tools effectively when working on a registered codebase.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
grafel-help
cajasmota
Overview of the grafel skill family.
SkillBFreshness: B★ 24Claude Code +9 - 0.601score
grafel-graph-read
cajasmota
Shared grafel read protocol — status → inspect → expand.
SkillBFreshness: B★ 24Claude Code +9
Signals
- Stars
- 24
- Forks
- 7
- Open issues
- 282
- Last commit (this folder)
- Jun 24, 2026 (4 months ago)
- Last release
- Sep 23, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cajasmota/grafel
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cajasmota
- 0.607score
grafel-graph-quality
cajasmota
Continuous health check of the grafel knowledge graph.
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
grafel-tech-docs
cajasmota
Generate the per-repo and group-level technical documentation set — overview, modules, reference, cross-cutting, group synthesis, cross-links, and patterns.
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
grafel-business-docs
cajasmota
Generate group-synthesised, PM-facing documentation — product capabilities, business domain glossary, user journeys as plain-language narratives, business…
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
grafel-feedback
cajasmota
Generate a privacy-preserving anonymized quality report for sharing with grafel maintainers, then layer an agent-driven "Findings & Interpretation" section on…
SkillBFreshness: B★ 24Claude Code +9 - 0.607score
grafel-security-audit
cajasmota
Two-phase security audit of the indexed group.
SkillBFreshness: B★ 24Claude Code +9 - 0.604score
grafel-help
cajasmota
Overview of the grafel skill family.
SkillBFreshness: B★ 24Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get grafel-aware-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
grafel-aware-review skill. Agent Mart. https://agentmart.dev/skills/cajasmota-grafel-aware-review (last updated 2026-10-24)