ktg-plugin-marketplace/plugins/ultraplan-local/CLAUDE.md

ultraplan-local

Deep implementation planning and research with an explicit brief step, specialized agent swarms, external research, adversarial review, session decomposition, disciplined execution, and headless support. A local alternative to Anthropic's Ultraplan.

Design principle: Context Engineering — build the right context by orchestrating specialized agents. Each step in the pipeline (brief → research → plan → execute) produces a structured artifact that the next step consumes.

Commands

Command	Description	Model
/ultrabrief-local	Brief — interactive interview produces a task brief with explicit research plan; optionally orchestrates the pipeline	opus
/ultraresearch-local	Research — deep local + external research, produces structured research brief	opus
/ultraplan-local	Plan — brief-reviewer, explore, plan, review. Requires --brief or --project	opus
/ultraexecute-local	Execute — disciplined plan/session-spec executor with failure recovery	opus

/ultrabrief-local modes

Flag	Behavior
(default)	Dynamic interview until quality gates pass → brief.md with research plan
--quick	Compact start; still escalates if required sections are weak or the brief-review gate fails → brief.md with research plan

Always interactive. Phase 3 is a section-driven completeness loop (no hard cap on question count); Phase 4 runs a brief-reviewer stop-gate with max 3 review iterations. After writing the brief, asks the user to choose manual (print commands) or auto (Claude runs research + plan in foreground).

/ultraresearch-local modes

Flag	Behavior
(default)	Interview + background research (local + external) + synthesis + brief
--project <dir>	Write brief to {dir}/research/{NN}-{slug}.md (auto-incremented)
--quick	Interview (short) + inline research (no agent swarm)
--local	Only codebase analysis agents (skip external + Gemini)
--external	Only external research agents (skip codebase analysis)
--fg	All phases in foreground (blocking)

Flags combine: --project <dir> --local --fg, --external --quick.

/ultraplan-local modes

Flag	Behavior
--project <dir>	Required path A — read {dir}/brief.md, auto-discover {dir}/research/*.md, write {dir}/plan.md
--brief <path>	Required path B — plan from a specific brief file; write to .claude/plans/ultraplan-{date}-{slug}.md
--research <brief> [brief2]	Enrich with extra research briefs beyond what is in {project_dir}/research/
--fg	All phases in foreground (blocking)
--quick	Plan directly (no agent swarm)
--export <pr|issue|markdown|headless> <plan>	Generate shareable output from existing plan
--decompose <plan>	Split plan into self-contained headless sessions

Breaking change (v2.0): one of --brief or --project is required. There is no interview inside /ultraplan-local. The --spec flag has been removed — use /ultrabrief-local to produce a brief instead.

/ultraexecute-local modes

Flag	Behavior
(default)	Execute plan — auto-detects Execution Strategy for multi-session
--project <dir>	Read {dir}/plan.md, write {dir}/progress.json
--resume	Resume from last progress checkpoint
--dry-run	Validate plan structure without executing
--validate	Schema-only check — parse steps + manifests, report READY | FAIL, no execution
--step N	Execute only step N
--fg	Force foreground — run all steps sequentially, ignore Execution Strategy
--session N	Execute only session N from plan's Execution Strategy

Agents

Agent	Model	Role
planning-orchestrator	opus	Runs full planning pipeline as background task (brief-driven)
research-orchestrator	opus	Runs full research pipeline as background task
architecture-mapper	sonnet	Codebase structure, tech stack, patterns
dependency-tracer	sonnet	Import chains, data flow, side effects
task-finder	sonnet	Task-relevant files, functions, reuse candidates
risk-assessor	sonnet	Risks, edge cases, failure modes
test-strategist	sonnet	Test patterns, coverage gaps, strategy
git-historian	sonnet	Recent changes, ownership, hot files
research-scout	sonnet	External docs for unfamiliar tech (conditional, planning only)
convention-scanner	sonnet	Coding conventions: naming, style, error handling, test patterns
brief-reviewer	sonnet	Task brief quality (5 dimensions: completeness, consistency, testability, scope clarity, research plan validity)
plan-critic	sonnet	Adversarial plan review (9 dimensions)
scope-guardian	sonnet	Scope alignment (creep + gaps)
session-decomposer	sonnet	Splits plans into headless sessions with dependency graph
docs-researcher	sonnet	Official documentation, RFCs, vendor docs (Tavily, MS Learn)
community-researcher	sonnet	Community experience: issues, blogs, discussions
security-researcher	sonnet	CVEs, audit history, supply chain risks
contrarian-researcher	sonnet	Counter-evidence, overlooked alternatives
gemini-bridge	sonnet	Gemini Deep Research second opinion (conditional)

Architecture

Brief: 7-phase workflow: Parse mode → Create project dir → Phase 3 completeness loop (section-driven, no question cap) → Phase 4 draft/review/revise with brief-reviewer as stop-gate (max 3 iterations; gate = all dimensions ≥ 4 and research plan = 5) → Finalize (brief.md on pass, or brief_quality: partial on cap/force-stop) → Manual/auto opt-in → Stats. Always interactive. Auto mode blocks foreground until plan is ready.

Research: 8-phase workflow: Parse mode → Interview → Background transition → Parallel research (5 local + 4 external + 1 bridge) → Follow-ups → Triangulation → Synthesis + brief → Stats. With --project, writes to {dir}/research/NN-slug.md.

Plan: 12-phase workflow: Parse mode (validate brief input) → Background transition → Codebase sizing → Brief review (brief-reviewer) → Parallel exploration (6-8 agents) → Deep-dives → Synthesis → Planning → Adversarial review (plan-critic + scope-guardian) → Present/refine → Handoff. With --project, writes to {dir}/plan.md.

Decompose: Parse plan → Analyze step dependencies → Group into sessions → Identify parallel waves → Generate session specs + dependency graph + launch script.

Execute: Parse plan → Security scan (Phase 2.4) → Detect Execution Strategy → Single-session (step loop) or multi-session (parallel waves via claude -p with scoped --allowedTools) → Phase 7.5 manifest audit → Phase 7.6 bounded recovery (if partial) → Report. With --project, reads {dir}/plan.md and writes {dir}/progress.json.

Security: 4-layer defense-in-depth: plugin hooks (pre-bash-executor, pre-write-executor), prompt-level denylist (works in headless sessions), pre-execution plan scan (Phase 2.4), scoped --allowedTools replacing --dangerously-skip-permissions. Hard Rules 14-16 enforce verify command security, repo-boundary writes, and sensitive path protection.

Pipeline: /ultrabrief-local produces the task brief. /ultraresearch-local --project <dir> fills in {dir}/research/. /ultraplan-local --project <dir> reads brief + research to produce {dir}/plan.md. /ultraexecute-local --project <dir> executes and writes {dir}/progress.json. All artifacts live in one project directory.

State

All artifacts in one project directory (default):

• Project root: .claude/projects/{YYYY-MM-DD}-{slug}/
  • brief.md (task brief from /ultrabrief-local)
  • research/{NN}-{slug}.md (research briefs from /ultraresearch-local --project)
  • plan.md (from /ultraplan-local --project)
  • sessions/session-*.md (from --decompose)
  • progress.json (from /ultraexecute-local --project)

Legacy paths (still work without --project):

• Research briefs: .claude/research/ultraresearch-{date}-{slug}.md
• Plans: .claude/plans/ultraplan-{date}-{slug}.md
• Sessions: .claude/ultraplan-sessions/{slug}/session-*.md
• Launch scripts: .claude/ultraplan-sessions/{slug}/launch.sh
• Progress: {plan-dir}/.ultraexecute-progress-{slug}.json

Stats:

• Brief stats: ${CLAUDE_PLUGIN_DATA}/ultrabrief-stats.jsonl
• Plan stats: ${CLAUDE_PLUGIN_DATA}/ultraplan-stats.jsonl
• Exec stats: ${CLAUDE_PLUGIN_DATA}/ultraexecute-stats.jsonl
• Research stats: ${CLAUDE_PLUGIN_DATA}/ultraresearch-stats.jsonl

Terminology

• Task brief — produced by /ultrabrief-local. Declares intent, goal, and research plan. Drives planning.
• Research brief — produced by /ultraresearch-local. Answers a specific research question. Feeds planning.

A project typically has 1 task brief and 0–N research briefs.