Agent
Maps architecture patterns and conventions in an existing codebase. Dispatched by /spec for brownfield projects. Read-only.
Agent
Maps architecture patterns and conventions in an existing codebase. Dispatched by /spec for brownfield projects. Read-only.
Agent
Quick brownfield orientation for a target area (endpoints, data models, UI, test coverage, recent history) -- capped at 80 lines, throwaway context for a spec about to be written. Dispatched by /spec, /test-plan. Read-only.
Agent
Deep, uncapped, source-cited feature inventory for one module of a target project -- every entry point gets a file:line citation and a behavior contract; adds a MIGRATE table + parity contract when the request names a port/migration target. The definitive deliverable, not throwaway context (see research-context for…
Agent
Finds landmines and risks in a codebase area before new work begins. Dispatched by /spec for brownfield projects. Read-only.
Agent
Maps the technology stack of an existing codebase. Dispatched by /spec for brownfield projects. Read-only.
Agent
Responds to code review feedback with technical rigor, not performative agreement. Verifies before implementing. Pushes back when reviewer is wrong. Read-only by design (proposes fixes; the user decides whether to apply).
Agent
Deep security review of code changes. Read-only. Dispatched by /review-team for focused security analysis. More thorough than /review's built-in security checks.
Agent
Behavior-preserving AI-slop strip pass. Given a base ref, scans the branch diff and applies surgical edits that strip AI-generated smell (redundant comments, over-defensive handling, unnecessary casts, flattenable nesting, patterns inconsistent with the file) before merge. Never changes behavior unless fixing a real…
Agent
Runs the whole assembled project's test suite end to end as the dynamic right-arm mirror of the design phase. Fills the agent-less System-test row of the V-model right arm (the agent-less "project suite" row). Read-only -- cannot modify the codebase.
Agent
Verifies a completed task against its spec acceptance criteria. Run after each worker subagent completes a task. Read-only -- cannot modify the codebase.
Agent
Turns a reviewed test-plan coverage matrix into runnable test code, one case per matrix row, in the repo's existing test framework. Write-capable. Dispatched by /kit:test-write after a SOLID ## Test plan critique verdict, before the real test run becomes the verifier.
Command
Maintainer-only: audit the kit's upstream sources (Credits drift + seed-rescan) and draft a dated, proposal-only absorption report. Does not execute, does not merge.
Command
Adopt the current (or a target) repo into the dwarves-kit operate-contract: inject AGENTS.md + a CLAUDE.md loader + a WORKFLOW pointer + the proof marker, idempotently, and wire the lane/loop-type/proof classifiers so the ship-gate engages.
Command
Turn a backlog item (ID-NNN) into a scoped goal draft and route it into the right WORKFLOW lane. Writes .claude/goals/, never executes.
Command
Systematic debug loop: root cause before any fix. Four phases, an evidence ledger, the 3-fix architecture wall.
Command
Opt-in interactive solution-design beat between /think and /spec. Explores 2-3 approaches one question at a time, holds for your approval per section, writes the Solution into the brief.
Command
Parallel multi-lens critique of a solution design (the active spec if present, else the decision brief). Dispatches 5 engineering lenses, merges findings, reports a verdict. Report-only, never blocks.
Command
Fire several disjoint VALIDATED specs concurrently, each in its own worktree, then converge. Cross-goal fan-out behind a disjointness gate + drift guard; lead-owned merge, no DAG.
Command
Update all project documentation to match the current codebase. Cross-references the diff against every doc file and fixes drift.
Command
Meta-agent agent-builder. From a one-line description, generates a new subagent definition OR a mega-goal sub-goal file and (by default) installs the subagent so it is dispatchable next session. --draft stops at a staged draft for review.
Command
Autonomous spec execution with verification. Dispatches worker subagents per task, verifies each with task-verifier, retries fixable failures (max 2), escalates the rest.
Command
Turn a merged change into a literate-diff explainer a human READS to understand: background -> goal + intuition -> a prose-ordered diff -> a diagram. Composes narrate-log + svg-knowledge-diagram; grounded in the actual diff + test results, never the agent's narrative.
Command
Build or refresh a source-cited, agent-checkable feature inventory for ANY target project you point it at: per-module spec + a top-level checklist. Works standalone (what does this codebase do) or as a migration source of truth (what needs porting). Refresh mode is an audit-loop instance, sibling to the…
Command
Onboarding gauntlet: a bounded-revise loop that converges a repo's contributor surface (docs + scripts + card template) by making a synthetic-dev agent onboard from the docs alone in a fresh clean room, build one seed card, and submit. Each round persists a full run record; the orchestrator revises the surface, tears…