dh

Plugin dh from marketplace jamie-bitflight-skills in Jamie-BitFlight/claude_skills. Commands read from the repo's manifest — 25 days ago.

Skills (79)

• add-new-feature

  SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.

• analyze-change-impact

  Analyze the causal system-wide impact of a proposed change across behavior, interfaces, state/data, runtime dependencies, tests, documentation, controls, people/processes, and model/prompt/context behavior. Use before planning when lexical reference search is insufficient to establish blast radius a

• analyze-test-failures

  Use when analyzing failing test cases to determine whether failures indicate genuine bugs or test implementation issues. Activates on "analyze failing tests", "debug test failures", "investigate test errors", or when provided with specific failing test names or output. Applies balanced investigative

• api-state

  Fetch and report current API syntax, changelog entries, and breaking changes for a specific library or protocol version. One research angle within a parallel technical-research set — runs independently and returns a structured cited report. Invoke when a specific library name and version are the tar

• audit-documentation-drift

  Audit documentation claims against implementation and authoritative repository evidence. Use when checking whether README, architecture, configuration, API, usage, or feature documentation is stale, incomplete, contradicted by code, missing implemented behavior, or inconsistent with a normative cont

• backend-resolution

  How to determine which backlog backend a project is configured to use, and what to do with the answer. Use when about to call a backend-specific tool, choosing between a GitHub-only and a Beads-native operation, or reporting which store a result came from.

• clear-cove-task-design

  Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md instructions that must be unambiguous, verifiable, and resistant to hallucination. Applies CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) to structure and write agent task prompts, then adds CoVe (

• code-review-architecture

  Use for architecture review, dependency graphs, coupling analysis, or circular dependency detection. Establishes project module namespaces and traces imports plus Claude plugin hook, skill, script, PEP 723, and MCP boundaries. Emits partitioned Mermaid graphs with cycle, coupling, and ownership sign

• code-review-claude-skills

  Reviews skill, agent, and plugin artifacts against their intended consumer's schema and runtime contract. Loaded by dh:code-reviewer for SKILL.md, agent definitions, or plugin manifests; checks discovery, frontmatter, triggers, tools, context cost, bundled references, and caller handoffs.

• code-review-cli

  Reviews CLI application code for correctness and quality. Use when reviewing tools that use argparse, click, typer, commander.js, or similar argument parsers — covers exit codes, help flags, stdin/stdout/stderr separation, non-interactive operation, signal handling, argument validation, ANSI color s

• code-review-llm

  Reviews LLM integration, prompt templates, model selection, token/cost budgets, evaluation harnesses, structured outputs, retries, and streaming. Checks trust boundaries and task evidence against the selected provider/model contract rather than prescribing universal model tiers or sampling settings.

• code-review-nodejs

  Reviews Node.js runtime behavior in JavaScript or TypeScript, including server entrypoints, route handlers, middleware, streams, processes, dependencies, and environment configuration. Loads alongside language and CLI checks when applicable; investigates blocking I/O, backpressure, injection, lifecy

• code-review-python

  Reviews Python boundaries, typing, error handling, tests, dependencies, and supported-version idioms against the target project's contracts and active tools. Loaded by dh:code-reviewer for Python source; uses Python-engineering standards when available and retains standalone checks otherwise.

• code-review-typescript

  Provides TypeScript-specific code review patterns covering strict mode, ESM, type safety, branded types, discriminated unions, async patterns, runtime safety, and common anti-patterns. Activates on detection of tsconfig.json, *.ts, or *.tsx files during code review — loaded automatically by dh:code-

• code-review-web

  Reviews browser-rendered HTML, CSS, JSX, TSX, JavaScript, and TypeScript for accessibility, XSS, forms, focus, rendering performance, styles, and lifecycle cleanup. Loaded by dh:code-reviewer when source or framework entrypoints establish frontend execution; composes with TypeScript checks.

• codebase-auditor

  Local codebase analysis research angle — derives behavioral contracts, coding conventions, SKILL.md flow insertion points, and agent data availability maps from actual source files. Use when the blocking question is answered by reading the repository: what does this function actually do, what patter

• codemod-runner

  Execute large-scale automated code transformations safely and idempotently. Use when renaming symbols across a codebase, migrating API call-sites, enforcing new patterns at scale, or applying structural edits to many files at once. Triggers on: 'codemod', 'mass rename', 'migrate all usages', 'transf

• complete-implementation

  Use when all tasks for a feature are marked COMPLETE — runs holistic quality gates including code review, feature verification, integration check, documentation drift audit and update, and context refinement. Creates follow-up plans when issues are found.

• complete-milestone

  Close a completed GitHub milestone. Args: {milestone-number}. Audits open and closed issues, offers to carry forward open items to a new or existing milestone, closes the GitHub milestone, updates Project V2 Status to Done for closed issues, and generates a completion summary. Use when a sprint or r

• comprehensive-test-review

  Review test effectiveness against authoritative contracts, relevant fault detection, refactor tolerance, boundary fidelity, isolation, and diagnostic value. Use when auditing test quality, reviewing coverage gaps, improving regression protection, or assessing tests after a change.

• context-integration

  Use when the PLAN artifact from SAM Stage 2 needs contextualization against actual codebase state — grounds the design plan in reality by performing scope analysis (NEW/MODIFY/COMPLETE classification), conflict detection between plan assumptions and codebase patterns, and resource mapping to concret

• create-artifact

  Register a plan artifact via the MCP backlog server. Use when you produce a document or report that downstream agents or worktree-isolated environments need to retrieve — feature-context, codebase-analysis, architect, T0-baseline, TN-verification, or research artifacts. Triggers include "store an ar

• development-harness

  Routes to the correct dh skill entry point by intent. Use when unsure which development-harness skill to invoke, starting a development workflow, or invoking /dh directly. Covers capture, groom, plan, execute, single task, quality gates, and milestone routing.

• dh-cli-usage

  Gives the dh CLI command and the directory of dh's scripts, both resolved from this skill's own directory. Use before running a dh plan, backlog, artifact or dispatch command, or a script from dh's scripts directory, and when an mcp__plugin_dh_* server failed to connect.

• dh-glossary

  One-line definitions of development-harness (dh) plugin terminology — RT-ICA, ARL, SAM, the S1-S7 pipeline stage names, Impact Radius — each with a pointer to its canonical source file. Use when a dh skill, agent, or workflow step references a term without defining it, before guessing what the term

• dh-meta-docs

  Development harness plugin documentation index. Use when looking up SAM pipeline, backlog lifecycle, SDLC layers, task/plan schema, plan artifacts, quality gates, impact analysis, or dispatch schema documentation.

• discovery

  Use when starting a new feature, gathering requirements for an unfamiliar domain, refining a vague idea into actionable scope, or when a user request is ambiguous or underspecified. Conducts SAM Stage 1 discovery — structured requirements gathering through user discussion, asking WHO/WHAT/WHEN/WHY a

• dispatch-contract

  Which agent a dh workflow dispatches, and the artifact consumer invariant.

• dispatch

  Orchestrate parallel agent dispatch as a manager — not a micromanager. Use when coordinating 2+ independent workers, running SAM task waves, relaying discoveries between worker waves, handling blockers, or synthesizing results. Covers both SAM structured dispatch (the task does the work) and ad-hoc

• ecosystem-research

  Research community usage patterns, real-world gotchas, and client compatibility for a specific known library, tool, or protocol feature. Use when a technical-researcher orchestrator needs community-sourced evidence about a named library or feature — bug reports, workarounds, compatibility gaps, and

• evaluate-acceptance-criteria

  Execute structured acceptance checks and record their observed results for later comparison. Use to capture a pre-change baseline or a post-change verification state without treating expected nonzero baseline results as execution failure.

• evaluate-sdlc-layers

  Evaluate and iterate on the SDLC Layer Separation Architecture implementation. Runs validation checks (cross-references, doc completeness, layer metadata, integration points), produces a findings report, and supports iterative fixes. Use when validating first-pass implementation, before claiming lay

• execution

  Executes SAM Stage 5 — opens an attempt on a single ARTIFACT:TASK, dispatches it to a fresh stateless agent session, runs quality gates, and records an ARTIFACT:EXECUTION with implementation results and verification output on the task. Use when Stage 4 Task Decomposition is complete and tasks are re

• fact-check

  Verify multiple factual claims in backlog items, skill documentation, or plugin content. Extracts discrete claims, delegates each to the canonical factual-verification process, and aggregates VERIFIED/REFUTED/INCONCLUSIVE results. Use for "fact check", "verify claims", or a set of unverified factual

• file-classification

  Classify changed prose files into review tiers before deciding SKIP. Use when reviewing a diff containing prose files.

• final-verification

  Certifies that a feature achieves its original objectives via goal-backward verification (SAM Stage 7). Use when all tasks pass forensic review — starts from expected outcomes, works backwards to verify each was achieved, and returns CERTIFIED or NOT_CERTIFIED with specific gaps.

• find-cause

  Investigate why something happens — confirm the question and success criteria with you, then trace the root cause with an evidence chain.

• forensic-review

  Use when SAM Stage 5 Execution has completed and task results need independent verification against acceptance criteria. Dispatches a separate reviewer agent to fact-check implementation outputs and returns COMPLETE or NEEDS_WORK with specific findings and remediation tasks.

• gate-push

  Single-verb branch-to-PR quality gate pipeline. Use when the user wants to gate, push, and open a PR for a branch in one command.

• generate-task

  Generates one worker task prompt conforming to the CLEAR + selective CoVe task design standard and swarm-task-planner structure. Use when creating or rewriting a single task entry or task block inside a plan — providing a title and brief description as input.

• groom-milestone

  Grooms a GitHub milestone for parallel execution — batch-grooms ungroomed items, assesses scope gaps, analyzes cross-item dependencies via Impact Radius overlap, builds conflict groups, assigns items to execution waves, and persists the dispatch plan via dispatch_create_plan MCP tool. Calls dispatch

• group-items-to-milestone

  Use when assigning backlog items to a GitHub milestone. Args: {milestone-number} [P0|P1|P2|title-filter]. Uses backlog list to load items, shows items with GitHub Issue status, lets user select which to assign. Creates missing GitHub Issues for selected P0/P1 items, assigns all to the milestone, upd

• hypothetical-walkthrough

  Use when the user asks for a hypothetical walkthrough of a system to expose tensions, frictions, gaps, or contradictions between its expected and evidenced flow.

• impact-measurement

  Quantitative cost measurement for technical research — token injection costs, payload sizes, context window consumption, and file-level counts from actual repo files. Use when a technical-researcher orchestrator needs the cost dimension of adding or changing something: how many tokens will it inject

• implement-feature

  Use when the plan_ref returned by add-new-feature is provided. Executes the SAM implementation loop — opens an attempt per ready task, dispatches each to a specialist agent in parallel, settles and judges what comes back, manages bookend tasks (T0 baseline capture and TN verification), and tracks co

• implementation-manager

  Manages feature implementation task state via SAM MCP tools. Use when querying task status, listing ready tasks, dispatching tasks for execution, updating task timestamps, or coordinating multi-task feature rollout. Activated by the /dh:execution orchestrator to track progress — also activates direc

• interop

  Routes a Superpowers plan file through the /work-backlog-item pipeline and writes SAM task back-references and chunk annotations into the original plan. Use when given a path to a Superpowers plan file via $ARGUMENTS and needing to create a linked backlog item plus SAM task plan.

• kage-bunshin

  Spawn and manage persistent interactive Claude Code CLI sessions with bidirectional communication via tmux. Provides spawn, send, read, status, list, and kill subcommands for orchestrating parallel peer sessions. Uses built-in --worktree and --tmux flags. Sessions stay alive for multi-turn steering.

• multi-perspective-review

  Use when a diff needs four parallel perspective reviewers (Security, Performance, Quality, Accessibility). Creates an ephemeral SAM plan, collects structured verdicts, synthesizes them into one deduplicated cross-referenced punch list, prints one summary line per perspective, and exits non-zero if a

• planner-rt-ica

  Same reverse-thinking method as dh:rt-ica (see dh:rt-ica or dh-glossary for the definition), but localizes any MISSING input to the affected task only, as a non-blocking information-completeness pre-pass before task decomposition and plan generation. Use when grooming backlog items, generating plans

• planning

  Use when Stage 1 Discovery is complete and design must begin — transforms the ARTIFACT:DISCOVERY into an actionable ARTIFACT:PLAN via RT-ICA prerequisite verification. Produces approach, components, success criteria, acceptance tests, and risks. Blocks on missing prerequisites before design proceeds

• research-note

  Synthesis step in the multi-angle technical research pipeline. Receives structured outputs from all four research angles (api-state, ecosystem-research, impact-measurement, codebase-auditor), applies cross-angle signal weighting and conflict resolution, and produces a single synthesized Research sec

• reuse-before-build
• review-accessibility-change
• review-performance-change
• review-principles
• review-quality-change
• review-security-change
• review-verdict-contract
• root-cause-tracing-process
• rt-ica
• setup-skill-discovery
• start-task
• subagent-contract
• synchronize-documentation
• synthesize-review-findings
• task-decomposition
• test-designer
• test-failure-mindset
• test-reviewer
• validate-implementation-plan
• validation-protocol
• verify-done
• verify-factual-claim
• verify-feature-outcomes
• verify-implementation-contracts
• verify-integration
• work-backlog-item
• work-milestone

Subagents (28)

• alignment-analyst

  Detects divergence between a proposed backlog-item change and the stated mission, design principles, and historical direction of whatever the change touches. Use when grooming a backlog item to verify the proposed change aligns with the governing product goals. Resolves mission sources nearest-first

• backlog-item-groomer

  Produce groomed content for a backlog item - discovers related skills, agents, prior work, artifact type, behavioral boundary, and dependency graph; performs RT-ICA assessment; returns the groomed item template for the orchestrator to store via the backlog grooming operation. Activate when preparing

• classifier

  Classifies a backlog item into one of five issue types (procedural, recurring-pattern, defect, missing-guardrail, unbounded-design) and conditionally runs root-cause analysis. Use when grooming a backlog item that requires issue type classification. Reads the item description, walks the classificati

• code-reviewer

  SAM Stage 6 independent code reviewer. Reviews any language or stack against a SAM task's acceptance criteria. Detects the stack from files, loads the matching dh:code-review-{stack} skill, checks universal quality dimensions (security, correctness, tests, API contracts, naming, error handling, perf

• codebase-analyzer

  Explores codebase patterns and registers structured analysis documents through the artifact operations. Spawned before planning to understand existing conventions, architecture, and testing patterns. Registers documents directly to reduce orchestrator context load.

• context-refinement

  Updates task context manifest with discoveries from current work session. Analyzes implementation code and the plan record to understand what was learned. Only updates if drift or new discoveries found. Provide the plan address and, when available, the owning item ID.

• contract-verification

  Post-task verifier that compares method signatures and type contracts from the architect spec against files modified by the just-completed task. Reads the architect spec Component Design and Type System Design sections, extracts expected signatures and contracts, then greps the modified files to fin

• dh-context-gathering

  Use when creating a new task OR when starting/switching to a task that lacks a context manifest. Provide the plan address (e.g. P{N}) so the agent can read it via sam_plan and write the context manifest back through the SAM update operation — never a file path, and never a direct file edit. Skip if

• doc-drift-auditor

  Audits documentation accuracy against implementation and authoritative repository evidence, then registers the audit as a DH artifact. Use as the DH subagent when a documentation-drift audit is required for a backlog item.

• ecosystem-researcher

  Researches domain ecosystems and technology landscapes before roadmap creation. Supports three modes - Ecosystem discovery, Feasibility assessment, and Comparison analysis. Use when exploring new domains, evaluating technology choices, or comparing implementation approaches. Requires MCP research se

• fact-checker

  Verify a single factual claim against primary sources. Use mcp__Ref__ref_read_url, mcp__exa__web_search_exa, mcp__context7__query-docs as primary research tools — training data recall is rejected as evidence. WebFetch/WebSearch are last-resort fallbacks only. Returns structured VERIFIED/REFUTED/INCO

• feature-researcher

  Researches feature requests and existing architecture documents to produce discovery context. Explores codebase patterns, identifies ambiguities, documents use scenarios, and surfaces questions for orchestrator resolution. Does NOT make technical implementation decisions.

• feature-verifier

  Goal-backward verification AFTER feature implementation. Starts from expected outcomes, works backwards to verify each was achieved. Tests the feature as a user would, not just that code exists. Returns VERIFIED or GAPS_FOUND with specific failures.

• impact-analyst

  Finds the causal, system-wide consequences of a proposed change across behavior, interfaces, data and state, runtime dependencies, tests, documentation, models and prompts, controls, people, and business processes. Use during backlog grooming or before planning when a change needs an evidence-backed

• integration-checker

  Verifies cross-module integration and end-to-end flows. Checks that new code connects properly with existing modules - exports used, imports work, data flows complete. Existence is not integration.

• plan-validator

  Validates implementation plans BEFORE execution begins. Checks for completeness, contradictions, missing dependencies, and executability. Returns READY or BLOCKED with specific gaps. Prevents wasted effort from flawed plans.

• review-synthesizer

  Synthesizes the four multi-perspective reviewer verdicts into one deduplicated, cross-referenced punch list. Loaded as the T5 profile by dh:multi-perspective-review.

• reviewer-accessibility

  Multi-perspective accessibility reviewer. Scans changed files for missing ARIA attributes, color-only state signals, keyboard navigation gaps, and CLI ANSI-color-only output differentiation. Returns SKIP when no UI changes are present (checked against the authoritative UI file pattern list in verdic

• reviewer-performance

  Performance-perspective reviewer for dh:multi-perspective-review. Scans changed files for N+1 query patterns, blocking synchronous I/O in async code paths, hot-loop allocations, and unbounded collection growth. Returns a structured verdict (APPROVE/REJECT/SKIP) per verdict-schema.md §2.1. SKIP when

• reviewer-quality

  Quality-perspective reviewer for multi-perspective code review. Investigates demonstrated correctness and maintainability defects, swallowed failures, unclear ownership, contract changes and consequential test gaps. Emits a structured verdict block (APPROVE/REJECT) written into the task's Review Res

• reviewer-security

  Security-perspective reviewer for dh:multi-perspective-review. Scans changed files for hardcoded secrets, injection vectors, authn/authz gaps, insecure deserialization, and dependency CVEs. Writes a structured JSON verdict block (APPROVE/REJECT/SKIP) per verdict-schema.md §2.1 into its task's Review

• rtica-assessor

  Assesses information completeness for a backlog item using the RT-ICA framework (AVAILABLE / DERIVABLE / MISSING). Use when grooming a backlog item and the grooming swarm has produced Impact Radius and Fact-Check sections that need to be evaluated for sufficiency before the groomer produces final co

• service-docs-maintainer

  Synchronizes documentation with code changes — use after implementing features, refactoring code, deleting files, changing APIs, or modifying configurations. Launch this agent whenever code changes could render existing documentation inaccurate or incomplete. Triggers include new endpoints added, mo

• swarm-task-planner

  Use when transforming architecture docs, PRDs, or feature specs into dependency-ordered task plans for parallel AI agent execution. Activates at SAM S4 task decomposition — produces priority-ordered SAM plans registered through the plan API, with acceptance criteria, sync checkpoints, and quality ga

• t0-baseline-capture

  Captures baseline state of structured acceptance criteria before implementation begins. Reads acceptance-criteria-structured from the SAM plan, runs each check-command, and registers the results as a T0-baseline artifact. Non-zero exit codes are expected and are NOT failures — this agent records wha

• task-worker

  Blank-canvas SAM task executor carrying the dh tools and skills a workflow needs — receives a task address and optional attempt number, reads the task from the work ledger, loads the specialist agent profile named by the task's agent field, then runs start-task. A dispatch-owned attempt adds runner

• technical-researcher

  Orchestrates multi-angle technical research by running four independent research skills in parallel (API state, ecosystem context, impact measurement, codebase audit), applying an internal review gate to detect cross-angle signals and conflicts, then synthesising a research note. Use when a backlog

• tn-verification-gate

  Verification gate that runs after all implementation tasks complete. Re-runs acceptance-criteria-structured check commands, compares results against T0 baseline, computes CriterionStatus per criterion, and registers a TN-verification artifact via MCP with a verdict of PASS or FAIL. FAIL blocks /comp

MCP servers (3)

• backlog

  runs: uv run --script scripts/run_backlog_server.py

• sam

  runs: uv run --script scripts/run_sam_server.py

• sequential_thinking

  runs: npx -y @modelcontextprotocol/server-sequential-thinking@latest

Hooks (7)

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start-session-id.cjs"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/inject-style-guide.cjs"

• UserPromptSubmit

  node "${CLAUDE_PLUGIN_ROOT}/hooks/inject-style-guide.cjs"

• TaskCompleted

  node "${CLAUDE_PLUGIN_ROOT}/hooks/task-completed-kage-bunshin-reminder.cjs"

• SubagentStop

  uv run --script "${CLAUDE_PLUGIN_ROOT}/skills/implementation-manager/scripts/task_status_hook.py"

• SessionEnd

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-end-kage-bunshin-cleanup.cjs"

• SessionEnd

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-end-kage-bunshin-child-notify.cjs"

Similar plugins