prove

Plugin prove from marketplace prove in mjmorales/claude-prove. Commands read from the repo's manifest — 1 month ago.

Skills (25)

• brainstorm

  Interactive brainstorming sessions for software architecture, product scoping, and general engineering. Use when the user wants to explore ideas, gather requirements, narrow down solutions, weigh trade-offs, or make technical decisions. Triggers on "brainstorm", "let's think through", "help me decid

• commit

  Semantic commit assistant. Reads scopes from .claude/.prove.json, detects scope gaps and offers to register new ones, groups changes into logical units, and creates conventional commits.

• comprehend

  Post-diff Socratic quiz that builds deep comprehension of agent-generated code. Analyzes recent changes, generates causal/design questions, quizzes the developer interactively, and logs comprehension gaps.

• create

  Create Claude Code skills, slash commands, subagents, or technical specs. Dispatches by type. Use when the user wants to create a new skill, new slash command, new subagent, new agent, write a spec, draft a specification, formalize a design, audit a spec, promote a decision record, or needs help wit

• curate

  Lift reasoning-log findings into durable scrum decisions at milestone close — the milestone-close curation pass that promotes findings into the durable decision store. Triggers on "curate", "curate the milestone", "promote findings", "journal to codex", "promote to decisions", "curate reasoning log"

• decompose

  Drive two structured-agent methodologies on prove primitives: the top-down decompose ladder (charter/VISION/milestone → epic → story → task) and AC-gated story-close. Triggers on "decompose", "decompose the milestone", "break this epic into stories", "ladder down", "decompose ladder", "close the sto

• docs

  Unified documentation skill. Generates human-readable docs (READMEs, guides, API references, getting-started), LLM-optimized agent/API docs, and regenerates CLAUDE.md. Triggers: "write docs", "document this", "README", "API reference", "getting-started", "LLM docs", "agent docs", "CLAUDE.md". For si

• index

  Build or update the content-addressable file index (CAFI) that gives agents routing-hint descriptions for codebase navigation. Triggers on "index the repo", "update the file index", "rebuild the index", "cafi", "file index". You are the driver: the `cafi plan` CLI emits the mechanical delta (walk, t

• intake

  Gather charter, team, or decomposition-kickoff answers through a self-contained HTML intake form instead of a conversational interview, then drive the same writer the conversation would. Triggers on "intake form", "fill out a form", "charter form", "team form", "decompose form", "HTML form", "render

• janitor

  Clean and compact prove's durable memory layers — team Lore, the Codex (scrum decisions), annotations, and contributor artifacts — keeping the tribal knowledge that grows team accuracy and folding away the rot. Triggers on "janitor", "clean the lore", "compact the lore", "compact the codex", "memory

• model-config

  Recommend and declare a project's Claude Code model configuration — the `models` block (opusplan hybrid, advisor pairing, fallback chain, effort) — and materialize it per machine. Triggers on "model config", "models preset", "set up the advisor", "advisor model", "opusplan", "which model should this

• nightshift-tick

  One tick of the night-shift driver: walk the priority ladder, do exactly one unit of work, exit. Invoked by the harness cron that /prove:nightshift on armed; also runnable once by hand to test a night. Triggers on "nightshift tick", "run one tick", "drive the night once".

• nightshift

  Enable, disable, or inspect night shift — the operator-opt-in overnight driver that drains a milestone's scrum tasks through the merge queue while the operator sleeps. Triggers on "night shift", "enable nightshift", "run overnight", "work on this overnight", "overnight autopilot", "disable nightshif

• notify

  Unified notification skill. Configures orchestrator reporters (Slack, Discord, MCP, custom) by generating bash scripts and updating .claude/.prove.json, and sends test notifications through configured reporters. Triggers: "notify setup", "set up notifications", "configure alerts", "slack reporter",

• orchestrator

  Autonomous task orchestrator with mode dispatch. Absorbs autopilot (plan-exists, skip PRD) and full-auto (no plan, requirements-first) as invocation modes. Auto-scales between simple mode (<=3 steps, sequential, no worktrees) and full mode (4+ steps, parallel worktrees with mandatory principal-archi

• plan

  Planning for tasks and individual steps. Use to plan a task (discovery-driven requirements gathering producing prd.json + plan.json for the orchestrator), plan implementation, or drill into a numbered plan step for design decisions, edge cases, and test strategy. Triggers on "plan a task", "plan thi

• plugin-cache-cleanup

  Prune stale cached versions of the prove plugin from Claude Code's plugin cache. Use when superseded versions pile up under plugins/cache and agents read stale skills/references from them, or when reclaiming plugin-cache disk space. Triggers on "clean up cached plugin versions", "prune the plugin ca

• prep-permissions

  Analyze the active task plan and .claude/.prove.json to configure .claude/settings.local.json with scoped permission rules. Use before orchestrator, autopilot, or implementation. Triggers on "prep permissions", "setup permissions", "configure permissions", "allow tools", "stop asking me".

• prompting

  Prompt engineering toolkit — craft optimized LLM prompts, manage the research cache, and count tokens. Dispatches to three subcommands. Use when the user wants to craft a prompt, write a prompt, generate a system prompt, create an agent prompt, optimize a prompt, do prompt engineering, manage the pr

• reasoning-brief

  Synthesize the 7-section risk-forward Review Brief from a run's reasoning log. Triggers on "reasoning brief", "review brief", "synthesize the brief", "generate the brief", "brief the run", "brief for review", "story brief". You are the driver: the `acb brief` CLI renders a mechanical preservation-sa

• run-migrate

  Apply model-driven CONTENT reshaping to stored run artifacts that sit behind the current schema, on explicit operator invocation only. Triggers on "migrate runs", "migrate run artifacts", "run content migration", "reshape run artifacts", "bring runs to current schema". You are the driver: the `run-s

• smart-compaction

  Anchor session context into prove primitives before compaction and rehydrate from them after. Built-in compaction summarizes by recency and drops the claude-prove state an agent needs to reorient; this skill externalizes volatile context into durable anchors (scrum tasks, decisions, run-state, a com

• steward

  Code quality audit and fix orchestration. Three modes — session review of branch diff (default), full deep audit with PCD pipeline + parallel fixes, iterative fix-audit loop bounded by max-passes. Invoked by /prove:steward, /prove:steward-review, /prove:auto-steward, steward, auto-steward, steward r

• task

  Task-lifecycle operations on orchestrator runs — handoff, pickup, resume context, progress, orchestrator status, complete task, merge task, task cleanup, archive task, clean artifacts. Dispatches subcommands: `handoff` serializes conversation context to .prove/handoff.md; `pickup` resumes from it; `

• workflow

  Execute a whole scrum milestone or a plan.json task tree as one parallel fan-out run. Triggers on "run the milestone", "execute milestone", "workflow", "fan out the milestone", "parallel milestone", "run the whole task tree", "milestone autopilot". Compiles the dependency graph to a plan, runs its t

Slash commands (29)

• /prove:brainstorm

  Explore options and record decisions via structured brainstorming

• /prove:bug-fix

  Structured debugging protocol — sequential hypothesis testing with backtracking

• /prove:cache-cleanup

  Prune stale cached prove plugin versions from Claude Code's plugin cache

• /prove:compact

  Anchor prove context before a /compact and rehydrate after — survive a context squeeze without losing claude-prove state

• /prove:comprehend

  Socratic quiz on recent diffs to build deep comprehension of agent-generated code

• /prove:create

  Create a new Claude Code skill, slash command, subagent, or technical spec.

• /prove:docs

  Unified docs — human/agent/both documentation and CLAUDE.md generation

• /prove:doctor

  Diagnose prove installation health — checks core config, tooling, and project drift

• /prove:index

  Build or update the content-addressable file index

• /prove:init

  Detect project tech stack, generate .claude/.prove.json, and bootstrap project-identity artifacts (charter, team, contributor)

• /prove:install-skills

  Install recommended community skills from external repos into ~/.claude/skills/

• /prove:intake

  Gather charter/team/decompose answers through an HTML intake form, then drive the same writer

• /prove:janitor

  Clean and compact team Lore, contributor artifacts, and the Codex via the memory-janitor agent — batch-gated, append-only

• /prove:local-env

  Point this machine at its claude-prove checkout — writes the per-machine env block into .claude/settings.local.json

• /prove:models

  Recommend, declare, and materialize the project's Claude Code model configuration (opusplan, advisor pairing, fallback, effort)

• /prove:nightshift-tick

  Run one tick of the night-shift driver (cron-invoked; also runnable by hand)

• /prove:nightshift

  Enable, disable, or inspect the overnight scrum-drain driver (night shift)

• /prove:notify

  Configure or test orchestrator notification reporters (Slack, Discord, MCP, custom)

• /prove:orchestrator

  Autonomous task orchestrator — dispatches autopilot (plan exists) or full-auto (PRD-first) modes

• /prove:plan

  Plan a task (discovery + prd.json/plan.json) or drill into a numbered step

• /prove:prompting

  Prompt engineering toolkit — craft prompts, manage the research cache, or count tokens.

• /prove:remember

  Append or update a directive in CLAUDE.md outside the prove-managed section

• /prove:report-issue

  Report a bug or feature request against the prove plugin via GitHub CLI

• /prove:review-ui

  Launch the prove review UI as a loopback daemon for inspecting runs, ACB intent groups, and verdicts

• /prove:scrum

  Agentic task management — backlog, milestones, tags, dep-graph, alerts

• /prove:steward

  Code quality audit — session review (default), full deep audit, or iterative auto-fix loop. Selects mode via flags.

• /prove:task

  Task-lifecycle dispatcher — handoff, pickup, progress, complete, cleanup

• /prove:update

  Validate configs, detect schema drift, and apply safe migrations

• /prove:workflow

  Execute a whole milestone or plan.json task tree as a parallel fan-out workflow

Subagents (12)

• brief-judge

  Stage-2 prose-quality judge for the reasoning-log Review Brief. Judges whether a synthesized brief's narrative is accurate, risk-forward, and coherent against the run's reasoning log. Read-only, advisory, non-blocking — preservation is proven mechanically by `acb brief validate` (Stage-1), so this j

• code-steward

  Post-agent code quality auditor. Deep codebase audit with surgical refactoring after parallel agent workflows.

• llm-prompt-engineer

  Prompt optimization specialist. Audits and rewrites prompts, agent definitions, system instructions, and CLAUDE.md files for LLM efficiency. Use when writing, reviewing, or improving any prompt or agent definition. Triggers on prompt optimization, token efficiency, instruction tuning, or LLM best pr

• memory-janitor

  Memory-layer curator for prove teams. Reads one team's full memory (Lore, annotations, contributor artifacts) or the project Codex (scrum decisions) and returns a keep/consolidate/promote/supersede plan that maximizes future accuracy per token. Read-only and plan-only — the janitor skill executes ev

• model-config-advisor

  Model-configuration strategist for prove projects. Reads a project's workload signals and returns a recommended `models` block (preset or custom pairing) with rationale and caveats. Read-only and plan-only — the model-config skill executes every write through `claude-prove models`. Invoked by the `m

• plan-backfiller

  Transforms an approved Claude Code plan-mode plan into structured prove artifacts (prd.json, plan.json) per the contract the driver supplies. Read-only and plan-only — the driving skill executes every file write and CLI call. Invoked by planning skills on the native planning route with the approved

• principal-architect

  Principal Architect for code review during orchestrated execution. Reviews implementation against requirements, checks architectural coherence, and approves or requests changes. Used by the orchestrator in full mode for mandatory review gates.

• product-visionary

  Strategic product agent for the scrum store. Owns vision alignment, milestone shaping, and macro dep-graph decisions. Reads `.prove/prove.db` directly; proposes writes via `claude-prove scrum` invocations after operator confirmation.

• scrum-master

  Operational scrum agent. Owns task-state transitions, dep-graph maintenance, stalled-WIP detection, and run/decision linkage on the unified prove store. Hook-driven (SessionStart, SubagentStop, Stop) and user-invoked via `/scrum task|milestone|tag|link`.

• spec-writer

  RFC/IETF-style specification author. Drafts, revises, and audits technical specs, protocol definitions, and format standards.

• technical-writer

  Senior technical writer that produces clear, human-readable documentation for projects, APIs, and modules. Delegates from the agentic-doc-writer skill or invoked directly when documentation needs to be written for human consumption. Use when creating READMEs, getting-started guides, architecture ove

• validation-agent

  Lightweight LLM validator that evaluates code changes against user-supplied prompt criteria. Used by the orchestrator validation gate for non-scriptable checks. Runs prompt-based validators defined in .claude/.prove.json.

MCP servers (1)

• playwright

  runs: npx @playwright/mcp@latest

Similar plugins