claudeboost

Plugin claudeboost from marketplace claudeboost-local in MikahNiehaus/ClaudeBoost. Commands read from the repo's manifest — 9 days ago.

Skills (26)

• bad-cop

  Spawn bad-cop directly on a diff that already passed its tests. Adversarial QA, writes tests aimed at breaking it, runs the code, adds logging, reports real provable failures. Reports only, fixes nothing. Stamps VERIFIED itself when it finds nothing, emits NITS when everything it found is nit severi

• code-quality-metrics

  Consider code quality metrics (complexity, maintainability, LOC) injected in context when making changes. Lower maintainability (<50) or high complexity (>15) warrant refactoring.

• codebase-understanding

  How researcher builds a structural picture of a codebase and checks a change against real engineering standards, before swiper ever looks at what to swipe. Covers the quality lenses (correctness, security, testing, maintainability), curating the import graph instead of dumping it, and when to reach

• debugging-methodology

  How to pick a debugging technique instead of guessing, and the tools and CLI recipes for every stack. Read this when a bug is not yielding after two or three attempts, when you are about to add another print statement, or before debugging a stack you have not touched before (React Native, .NET, nati

• doc-rag

  Gather official documents (statutes, regulations, any authoritative source) on any topic, chunk them at real citation boundaries, and build a persistent, searchable corpus inside clean-rag. Topic agnostic -- the schema is generic, your topic is whatever source list you write. Use to ingest a new top

• eyes

  WHEN doing browser QA, fixing UI issues, or when users express dissatisfaction with visual appearance or behavior; use Playwright MCP to capture screenshots and run a structured visual feedback loop. USE before calling any UI change done.

• fix-perm

  Paste a permission prompt you just hit and get the right rule to stop it recurring. Works out which rule actually fired, proposes the narrowest rule that covers the whole class of safe commands like it, refuses the dangerous broad option the prompt itself offers, tests the proposal against your live

• good-cop

  Spawn good-cop directly, only after /bad-cop found something Critical or High. Researches the root cause of bad-cop's findings, fixes it, gets every test green, and stamps the verifier gate with VERIFIED. Skip this entirely when bad-cop emitted VERIFIED (it found nothing) or NITS (nit severity only,

• graphrag

  Build or query the semantic code graph (true GraphRAG) for a project. An LLM reads the codebase and extracts entities plus the intent behind calls, imports, and dependencies, then answers cross file "how does X flow to Y" questions the import graph can't. Manual and resumable: a build runs overnight

• grill-me

  A relentless interview to sharpen a plan or design. Ask the whole answerable frontier at once, each question with a recommended answer, and send researcher and swiper after any fact instead of asking the human for it. Ends with a mermaid diagram of what got settled and what is genuinely still open.

• grilling

  Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

• human-voice

  Audit and rewrite prose so it reads as human written and is easy to understand. Use when asked to remove AI-isms, clean up AI writing, make something sound less like AI, or make an explanation clearer. Three modes: detect only, rewrite, and edit a file in place. Covers two separate problems, registe

• plan-cop

  Run the /workshop adversarial loop on a PLAN or a decision, with counterparty safety rules on top. You write the plan, bad-cop attacks it, good-cop revises it with cited grounding, and the loop repeats until bad-cop stamps VERIFIED on a clean pass. Use for any consequential non code decision, an ema

• pr-mp4

  WHEN a ticket is finished and the user wants a narrated video for the pull request, or asks for a PR walkthrough, PR mp4, proof video, or "show me it works" recording; build a deck covering only architecture and proof, embed the real QA screenshots at full size, narrate it, and verify the encode. US

• presentation

  WHEN the user asks for a presentation, a narrated explainer or walkthrough video, a slide deck, a PowerPoint or a .pptx, or asks to turn an explanation of any topic into slides. Builds a narrated explainer mp4 from HTML slides around real proof, with highlights timed to the voice; or a .pptx with py

• ps

  Quick mode for this turn. Use when you (the human) already know a change or question is trivial and needs no research or verification. Starting a turn with /ps deterministically stands down the research gate and the verifier for that turn, so a rename, a one line fix, a comment tweak, or a quick que

• quick-cop

  Spawn quick-cop on a claim. Cheap check that you actually did what you just said you did. Non blocking, stamps nothing, never satisfies the verifier gate and never replaces bad-cop. Use it liberally, backgrounded, every time you say something is done, finished, complete, or has no gaps.

• research-routing

  How a research agent decides what to search, where to search it, and how to turn a project's import graph into something useful. Covers depth vs breadth routing, the does-this-already-exist check, and per aspect coverage.

• research

  Send out the research agent on a question, with no code edit involved. Use when you want depth and breadth research on a decision, a design question, a "what's the best way to X", or "does this already exist" before committing to anything.

• researcher

  Spawn researcher directly on a task, no /start sequence attached. Use for a pure codebase structure or standards question, what breaks if this changes, what does good code for this look like here, without needing swiper's swipe check afterward.

• skill-from-memory

  Mine the project's memory store for recurring issues, then SWIPE an existing published skill that solves each one instead of writing a new skill by hand. Use when the user asks to turn memory, feedback, or recurring issues into skills, to find a skill for something that keeps coming up, or to check

• start

  Kick off a new build or feature the deliberate way. Spawns researcher first (codebase structure plus real engineering standards), then swiper informed by that (what can be swiped, never written by swiper itself), then builds a narrated teaching video of the open questions and the architecture, then

• swiper

  Spawn swiper directly on a task, no /start sequence attached. Use when you already know what needs checking (does this exist, what's the exact code or repo or StackOverflow answer to use) and don't need researcher's structural pass first.

• traps

  Lookup table of concrete reasoning failure modes that ship as bugs — dates and time zones, epoch units, mutation vs copy, async, floats and money, sort, division and modulo, regex and strings, familiar-API traps, closures in loops, boolean logic. Each row names the broken pattern and the fix. Read i

• walkthrough

  Generate an interactive step by step tutorial/walkthrough for any feature or workflow. Uses Playwright MCP in headed mode to navigate through the UI, inject visual annotations (highlights, numbered callouts, arrows, popovers) via JavaScript, capture annotated screenshots at each step, and assemble a

• workshop

  Workshop any subject by attacking it, not by thinking harder about it. Starts by asking what you are actually trying to achieve, checks whether the thing already exists, then writes an answer down, a fresh bad-cop attacks it, a fresh good-cop revises it with cited grounding, and the loop repeats unt

Hooks (30)

• SessionStart

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/compaction-restore.py"; elif comma

• SessionStart

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/workspace-primer.py"; elif command

• SessionStart

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/rag-session-reset.py"; elif comman

• SessionStart

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry-session.py"; elif comman

• SessionStart

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/session-restore-ledger.py"; elif c

• SessionStart

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/request-ledger.py"; elif command -

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/research-gate.py"; elif co

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/research-gate-bash.py"; el

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/graph-context-inject.py";

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/code-pattern-inject.py"; e

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/agent-spawn-gate.py"; elif

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/skill-verify-gate.py"; elif comman

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/workspace-boost-gate.py"; elif com

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/tdd-guard.py"; elif command -v pyt

• PreToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/bash-guard.py"; elif command -v py

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/research-record.py"; elif

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/verifier-record.py"; elif

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/verify-gate-cmd.py"; elif command

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/context-nudge.py"; elif command -v

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry-hook.py"; elif command -

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/comment-humanness-check.py"; elif

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/reindex-after-edit.py"; el

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/verify-after-edit.py"; eli

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/record-edit.py"; elif comm

• PostToolUse

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/lint-gate.py"; elif comman

• SubagentStop

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/clean-rag/hooks/verifier-record.py"; elif

• PreCompact

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/compaction-save.py"; elif command

• PreCompact

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/request-ledger.py"; elif command -

• UserPromptSubmit

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/session-primer.py"; elif command -

• UserPromptSubmit

  if command -v "$CLAUDEBOOST_PYTHON" >/dev/null 2>&1; then "$CLAUDEBOOST_PYTHON" "${CLAUDE_PLUGIN_ROOT}/clean-rag/portable/hook-run.py" "${CLAUDE_PLUGIN_ROOT}/scripts/speak-stop.py"; elif command -v py