Menu
Execute the REVIEW phase of the lifecycle via the `agf` CLI — blast radius insights, code-aware sync, mermaid visualization, quality feedback
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | graph-review |
| description | Execute the REVIEW phase of the lifecycle via the `agf` CLI — blast radius insights, code-aware sync, mermaid visualization, quality feedback |
| triggers | ["graph-review"] |
| version | 2.0.0 |
| author | Diego Nogueira |
| date | "2026-04-04T00:00:00.000Z" |
| toolchain | ["agf insights","agf export","agf metrics","agf gate","agf phase"] |
REVIEW phase via the agf CLI (zero MCP). Code review with real blast-radius analysis via agf insights, stale-reference detection, and quality gating before handoff.
agf phase reports REVIEWagf insights (impact) → agf insights (code sync) → agf export --format mermaid → agf metrics → agf gate review → agf phase HANDOFF
agf insights
Real upstream/downstream dependents per modified module — replaces manual guessing.
agf insights
Detects stale sourceRefs (deleted/moved files), missing testFiles (done tasks without test refs), symbol drift. Fix before proceeding.
agf export --format mermaid
Tabular: agf export --format csv.
agf metrics
Review velocity, quality (AC pass rates), complexity (sizes, dependency depth).
git diff main...HEAD
git log main..HEAD --oneline
Check: quality/readability, security (OWASP top 10), performance, error handling, test quality (not just coverage), ADR adherence from DESIGN.
Inspect RAG knowledge surfaced during implementation; flag unhelpful/outdated docs for prune. Use agf search "<q>" to see what the store returns. Improves future RAG retrieval.
agf gate review
Gate: all sprint tasks validated · code review done (blast radius analyzed) · no stale refs · metrics in range. Fail → return to IMPLEMENT/VALIDATE.
agf phase HANDOFF
Follow the nextAction from agf phase.
Phase: REVIEW → HANDOFF
Blast radius: N modules affected
Code sync: M stale refs, K missing testFiles
Changes: J files, L lines
Gate: review_ready — score N/100, grade X
Status: Ready for HANDOFF
REVIEW → HANDOFF: agf phase HANDOFF then $graph-handoff. Spiral: after tasks, agf savings / agf metrics --economy-report → agf learning → calibrate next turn.
agf insights blast radius — manual analysis misses transitive depsnextAction hintAGENTS.md and use apply_patch for manual edits.Economia de tokens. Os levers compartilhados por todas as skills —
--select,agf retrieve-command,agf exec chain, reuso antes de criação — vivem em_shared.md→ Token Economy. Fonte única: um parágrafo repetido em trinta arquivos é o trigésimo primeiro que envelhece sozinho.
Accessibility compliance audit using WCAG 2.2 AA standards, ARIA validation, screen reader testing, keyboard navigation, color contrast analysis, and i18n readiness
Execute the ANALYZE phase of the lifecycle via the `agf` CLI — PRD creation, requirements, Definition of Ready (7 checks), cross-project learning
API governance and design audit using OpenAPI/Swagger spec generation, REST maturity model, contract validation, and breaking change detection
Architecture governance using C4 Model, ADR lifecycle, Architecture Fitness Functions, layer boundary enforcement, and drift detection
Human-in-the-loop PLANNING skill — investigates the project (graph + git + harness/gaps) and runs the whole ANALYZE→DESIGN→PLAN chain in one faceted loop to produce a COMPLETE PRD injected as graph backlog (epics, tasks, testable AC) for a separate agent to implement. Applies the project's planning methodologies — Impact Mapping + OKR per epic, JTBD, MoSCoW, WSJF/Cost-of-Delay, User Story Mapping, Example Mapping (Rules/Examples → Given-When-Then AC), SPIDR splitting, INVEST, Definition of Ready, Risk Matrix; the full catalogue lives in the skill body. Stops for the human after each complete PRD and iterates the next cycle from the project's own findings (dogfood). Does NOT implement. Triggers — graph-backlog-generation, gerar backlog, criar PRD, planejar feature, detalhar épico, novo ciclo, "plan the next thing", "what should we build next".
Automated bug discovery through static analysis, LSP diagnostics, pattern detection, regression hotspot analysis, and error catalog mining