Agent
Writes child Epic-definition files for /epics from a structured handoff file — one file per Epic, following the Epic template, traceable to the jira-reader handoff and code-scanner evidence. Write-only — writes vault content, never commits (still true — it runs no git at all). Returns the list of Epic files written.…
Agent
Independently re-derives a grounding finding from its own source — the pinned repository for a [CG#n] or a class-4 [DG#n], the exported frame set for a design-only [DG#n] — and returns agree / extend / contradict / unprovable with its own evidence. It does NOT check citations — checking a citation only proves the…
Agent
Reviews app code and UI for compliance with public UI design-system and accessibility standards. Checks app header, data table, filter field, connections, permissions, settings, dashboards, accessibility/WCAG, terminology, and data naming. Triggers on 'review for guidelines', 'check compliance', 'UI guideline review'…
Agent
Ingests one idea source (inline prompt, a markdown file with wikilinks/images, a community post, or an exported Jira ticket — either product feedback (an RFE) or an existing Product Requirements Document the idea extends, parallels, or rewrites) from the user's vault and returns a structured source digest for /idea.…
Agent
Post-session maintenance agent. Reads what happened during an implementation, fix, or upgrade session and produces a structured Lessons Learned report with actionable suggestions for improving project tooling — CLAUDE.md rules, reference docs, hooks, command workflows, and new skill patterns. Suggest-only; does NOT…
Agent
Produces ONE interface proposal for ONE contested interface under ONE named design constraint, for /design's Phase 5 fan-out. Dispatched three times in parallel with different constraints so the takes diverge; the caller compares them on depth, locality, and seam placement. Read-only — proposes an interface, never…
Agent
Reads a pre-exported Jira markdown hierarchy (Product Requirements Document, Epics, Stories, Sub-tasks, Research, Request for Assistance) from the user's Obsidian vault and returns a structured handoff — linked items, PR URLs with host classification, and capability themes. Read-only; never modifies vault files. Model…
Agent
Reviews a Product Requirements Document ( .md) authored by /create-prd or /update-prd for goal crispness, user-story/acceptance-criteria testability, scope concreteness, internal consistency (no self-contradiction), measurable metrics, product-level purity (no implementation detail), downstream-contract frontmatter…
Agent
Cross-artifact readiness verifier for /ready. Reads the Jira workflow status and checks the ARD/spec/design artifacts justify it and the next transition. Returns SUPPORTED / PARTIAL / NOT-SUPPORTED. Uses Claude Opus. The only reviewer that does joint cross-artifact analysis; per-artifact quality is reviewed by…
Agent
Renders an example-docs release-notes draft (the authored body only) for a Jira PRD/ticket from the jira-reader handoff and optional PR-diff summaries. Emits exactly ONE Summary. Resolves the note's destination (breaking-changes / feature-updates / fixes) to pick the draft's shape — a {{#context}} label + H3 title +…
Agent
Applies targeted code fixes for BLOCKER and MAJOR findings from a code-review agent report. Returns a structured fix report; caller re-runs the review. Default model (not Opus).
Agent
Risk-weighted planner for SIGNIFICANT / HIGH-RISK tasks. Returns a structured plan with an explicit risks section. Uses Claude Opus. Do NOT use for SIMPLE / MODERATE tasks.
Agent
Reviews a product specification.md authored by /specify for per-stage quality (problem/scope/user-stories/acceptance-criteria/test-cases), cross-stage consistency, coverage, and identifier integrity. Read-only; returns findings + a PASS / PASS WITH RECOMMENDATIONS / BLOCK verdict. Uses Claude Opus.
Agent
Run the full test suite and return structured results for regression comparison. Operates in two modes — "capture" (run tests, record baseline) and "verify" (run tests again, diff against a provided baseline, return a structured regression report). Model tier assigned by the caller per the model-routing policy (no…
Agent
Writes tests for new or changed behavior based on a diff. Does NOT run tests. Framework detection mirrors test-baseliner; if no framework is detected, returns "not detected" immediately so the caller can ask the user whether to specify a test command or skip. Model tier assigned by the caller per the model-routing…
Agent
Agent for the upgrade workflow. Handles Phase 2 (execution) for a single component: apply the upgrade plan produced by upgrade-planner, run the build, verify tests via test-baseliner, and auto-fix any test code breakage caused by the new version's API changes. Invoked sequentially by the /upgrade command orchestrator.…
Agent
Agent for the upgrade workflow. Handles Phase 1 (compatibility planning) for a single component: detect the component in the repo, resolve the requested target version (exact, minor, latest, lts, or bare), and verify compatibility with all other components in the repo. Invoked in parallel by the upgrade orchestrator …
Agent
Read-only prior-art discovery for the idea-authoring commands. Given the user's vault root, a feature summary, and optional themes, searches Projects/Products/ and Projects/ideas/ for tracked initiatives that cover, precede, parallel, or are superseded by the new work, and returns a bounded digest — each match…
Agent
Agent for the vuln workflow. Handles the fix phase of CVE remediation: capture baseline via test-baseliner, apply the minimal version change produced by vuln-research, rebuild, verify tests via test-baseliner, commit to a new branch, and open a PR. Invoked sequentially by the fix-vuln orchestrator with a research…
Agent
Agent for the vuln workflow. Handles the read-only research phase of CVE remediation: NVD API lookup, library detection in the repository, current version discovery, and minimum safe version resolution. Invoked explicitly by the /vuln command orchestrator — NOT triggered by direct user prompts. Accepts a structured…
Command
Review OpenAPI specification files against REST API and IAM permission-naming guidelines. Runs a deterministic Spectral lint first where a Spectral CLI is available, then reviews what a linter cannot express. Checks version consistency, naming conventions, IAM scope format, HTTP status codes, and schema composition.
Command
BRD-grounding workflow (PA phase, second of the BRD-to-PRD route). Pins every mounted repository to a verified commit, grounds every [BR#n] claim against code (code-grounder) and an exported design frame set (design-grounder), independently re-derives every finding (grounding-verifier, Opus), and assigns each finding…
Command
BRD-intake workflow (PM phase, entry point of the BRD-to-PRD flow). Copies a customer-supplied business requirements document into the specs repo verbatim, dispatches brd-reader to extract a [BR#n] requirement inventory, confirms its defect candidates interactively against the six brd-format.md classes, and writes a…
Command
BRD decision workflow (PM phase, fourth command of the BRD-to-PRD route). Gates on the BRD's grounding being merged, every finding carrying a verifier outcome, and its coverage ledger fully allocated, then generates the round's question set and tags every question [G]/[V]/[C] before a single one is asked. Answers…