pan-wizard 3.8.0 → 3.12.0

package/README.md

@@ -1,16 +1,16 @@
 <div align="center">
 
-<img src="https://cdn.jsdelivr.net/npm/pan-wizard@latest/assets/pan-logo-2000-transparent.svg" alt="PAN Wizard" width="200" />
+<img src="assets/pan-readme-hero.png" alt="PanWizard — context engineering that makes AI coding reliable" width="820" />
 
-# PAN WIZARD
+# PanWizard
 
 **Project Automation Navigator — A lightweight workflow automation and context engineering system for Claude Code, OpenCode, Gemini CLI, Codex, and Copilot CLI.**
 
 **Solves context rot — the quality degradation that happens as Claude fills its context window.**
 
-[![npm version](https://img.shields.io/npm/v/pan-wizard?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/pan-wizard)
-[![npm downloads](https://img.shields.io/npm/dm/pan-wizard?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/pan-wizard)
-[![License](https://img.shields.io/badge/license-MIT-blue?style=for-the-badge)](LICENSE)
+[![npm version](https://img.shields.io/npm/v/pan-wizard?style=for-the-badge&color=FF5A3C&labelColor=211E18)](https://www.npmjs.com/package/pan-wizard)
+[![npm downloads](https://img.shields.io/npm/dm/pan-wizard?style=for-the-badge&color=5B4BE6&labelColor=211E18)](https://www.npmjs.com/package/pan-wizard)
+[![License](https://img.shields.io/badge/license-MIT-1E8E5A?style=for-the-badge&labelColor=211E18)](LICENSE)
 
 <br>
 
@@ -22,7 +22,7 @@ npx pan-wizard@latest
 
 <br>
 
-![PAN Install](https://cdn.jsdelivr.net/npm/pan-wizard@latest/assets/terminal.svg)
+![PanWizard bot army — Mission Control delegating to squads, builders in isolated worktrees, human-gated merge](assets/terminal.svg)
 
 <br>
 
@@ -74,6 +74,46 @@ PAN is the context engineering layer that makes Claude Code reliable. It breaks
 
 ---
 
+## Bot Army
+
+> **Don't run one phase — run the whole project.** `/pan:army` turns PAN's agents into a coordinated army that delivers a goal end-to-end: an Opus **Mission Control** plans the mission and delegates to specialist **squads**, parallel builders each work an isolated git worktree, and **nothing reaches your main branch without green checks and your explicit approval.**
+
+<div align="center">
+<img src="assets/pan-orchestration.png" alt="PanWizard specialist agents orchestrated along a pipeline" width="340" />
+</div>
+
+| Tier | Squad | Does | Access |
+|------|-------|------|--------|
+| **0 · Mission Control** | `pan-conductor` (Opus) | Plans + delegates. Never writes code. | delegation-only |
+| **1 · Architecture** | roadmapper · planner · researchers | Designs the contract before code | read-only |
+| **1 · Build** | `pan-executor` | Turns the contract into committed code | read / write · one `army/<task>` worktree per agent |
+| **1 · Quality** | reviewer · hardener · verifier · … | Adversarially tries to break it | read-only |
+| **1 · Release** | `pan-release` | Ships behind a human gate | always-ask |
+| **2 · Workers** | document_code · distiller | Narrow, high-volume jobs | scoped |
+
+**The loop:** `Muster → Plan → Delegate → Execute → Review → Integrate → Learn` ↺ — repeating until the goal ships or a stop condition fires.
+
+**Bounded by a hard safety harness:**
+
+- **A human merges. Always.** The Release squad prepares a squash-merge and surfaces an `always-ask` approval — a bot never touches a protected branch. Recovery is `git revert` or the previous tag, never a force-push.
+- **Isolated builders.** Each Build agent forks its own `army/<task>` branch + git worktree, so parallel agents never share a file.
+- **Caps that don't relax.** Delegation-depth cap, per-cycle spawn + budget ceilings, and a `.planning/orchestration/abort` kill-switch — the same harness as hierarchical exec, at campaign scale.
+
+**Run it over days.** `--schedule` arms a self-resuming campaign with a per-day budget that burns the backlog down across sessions — and *still* waits for you at every merge. **Autonomy runs up to the irreversible step; a human is at the step.**
+
+**Watch it live.** `/pan:hud` renders a single self-contained HTML dashboard — Mission Control over the squads, in-flight worktrees, campaign budget, telemetry, and the safety harness — in one page.
+
+```bash
+/pan:army "ship the v1 reporting module"     # plan → delegate → build → review → human-gated ship
+/pan:army "harden auth across the app" --schedule daily --daily-budget 200
+/pan:army --status        # where the campaign stands
+/pan:hud --open           # watch the army work, live
+```
+
+Resolve the live squad roster any time with `pan-tools squad list`.
+
+---
+
 ## Who This Is For
 
 People who want to describe what they want and have it built correctly — without managing complex project management overhead.
@@ -117,7 +157,7 @@ npx pan-wizard --claude --local    # Install to ./.claude/
 # OpenCode (open source, free models)
 npx pan-wizard --opencode --global # Install to ~/.config/opencode/
 
-# Gemini CLI
+# Gemini CLI (enterprise — see note below)
 npx pan-wizard --gemini --global   # Install to ~/.gemini/
 
 # Codex (skills-first)
@@ -134,6 +174,9 @@ npx pan-wizard --all --global      # Install to all directories
 
 Use `--global` (`-g`) or `--local` (`-l`) to skip the location prompt.
 Use `--claude`, `--opencode`, `--gemini`, `--codex`, `--copilot`, or `--all` to skip the runtime prompt.
+Add `--unified-skills` to install commands as one shared `.agents/skills/` tree read natively by every runtime (and Antigravity CLI) instead of per-runtime formats — see the User Guide for details.
+
+> **Gemini CLI note:** from June 18, 2026, Google's Gemini CLI serves Gemini Code Assist (Standard/Enterprise) customers; individual free / AI Pro / Ultra accounts are directed to Antigravity CLI instead. PAN's `--gemini` target installs for Gemini CLI. Antigravity CLI is not yet a PAN install target, but it reads the shared `.agents/skills/` tree natively — install with `--unified-skills` and PAN's commands are usable from Antigravity in the same project.
 
 </details>
 
@@ -534,6 +577,7 @@ PAN is not a replacement for your IDE or AI agent — it's the orchestration lay
 | Command | What it does |
 |---------|--------------|
 | `/pan:progress` | Where am I? What's next? (supports `health` subformat) |
+| `/pan:hud` (alias `/pan:dashboard`) | Render a self-contained HTML dashboard of project + bot-army state to `.planning/hud.html` (`--open`, `--out`, `--stdout`) |
 | `/pan:help` | Show all commands and usage guide |
 | `/pan:update` | Update PAN with changelog preview |
 | `/pan:discord` | Join the PAN Discord community |
@@ -544,6 +588,12 @@ PAN is not a replacement for your IDE or AI agent — it's the orchestration lay
 |---------|--------------|
 | `/pan:map-codebase` | Analyze existing codebase before new-project |
 
+### Bot Army
+
+| Command | What it does |
+|---------|--------------|
+| `/pan:army "<goal>"` | Campaign-scale delivery: Mission Control (Opus) delegates a whole-project goal to architecture/build/quality/release squads with branch-per-agent worktrees, behind CI + a human merge gate; `--schedule`/`--continue` run it over time |
+
 ### Phase Management
 
 | Command | What it does |
@@ -585,7 +635,7 @@ PAN is not a replacement for your IDE or AI agent — it's the orchestration lay
 | Command | What it does |
 |---------|--------------|
 | `pan-tools preflight [target]` | Pre-flight validation: state, blockers, git clean, config, error patterns |
-| `pan-tools dashboard` | Aggregated project overview: phase, progress, blockers, next action |
+| `pan-tools dashboard` | Aggregated project overview as JSON: phase, progress, blockers, next action (for the visual HTML dashboard, see `/pan:hud`) |
 | `pan-tools learnings extract` | Auto-extract learnings from sessions, error patterns, and summaries |
 | `pan-tools learnings list` | List all extracted learnings with type breakdown |
 | `pan-tools learnings prune` | Remove old learnings by age (`--days N`) or ID (`--id LEARN-NNN`) |
@@ -649,7 +699,7 @@ Control which Claude model each agent uses. Balance quality vs token spend.
 | `balanced` (default) | Opus | Sonnet | Sonnet |
 | `budget` | Sonnet | Sonnet | Haiku |
 
-> Simplified view — actual model assignment varies by agent role. See [User Guide](docs/USER-GUIDE.md#model-profiles) for the full per-agent breakdown.
+> Simplified view — actual model assignment varies by agent role. See [User Guide](docs/USER-GUIDE.md#model-profiles-per-agent-breakdown) for the full per-agent breakdown.
 
 Switch profiles:
 ```
@@ -783,6 +833,10 @@ This removes all PAN commands, agents, hooks, and settings while preserving your
 
 ## Documentation
 
+<div align="center">
+<img src="assets/pan-docs-header.png" alt="" width="720" />
+</div>
+
 | Document | Audience | What it covers |
 |----------|----------|---------------|
 | [User Guide](docs/USER-GUIDE.md) | Users | Workflow diagrams, command reference, config schema, troubleshooting |
@@ -808,6 +862,23 @@ MIT License. See [LICENSE](LICENSE) for details.
 
 ---
 
+## Brand
+
+| Token | Hex | Use |
+| --- | --- | --- |
+| Ember | `#FF5A3C` | Primary / CTAs |
+| Conduit | `#5B4BE6` | Links, agent connectors |
+| Verify | `#1E8E5A` | Success / verified |
+| Butter | `#FFCE4A` | Highlights |
+| Ink | `#211E18` | Dark surfaces, terminals |
+| Paper | `#F3ECDD` | Light surfaces |
+
+Type: **Gabarito** (display) + **JetBrains Mono** (code & labels). Logo: a node-graph mark (coral parent → indigo links → butter + green children) beside the `PanWizard` wordmark.
+
+> Banner, avatar, and illustration art are generated from the prompts in [`docs/branding/image-prompts.md`](docs/branding/image-prompts.md).
+
+---
+
 <div align="center">
 
 **Claude Code is powerful. PAN makes it reliable.**

package/agents/pan-conductor.md

@@ -1,10 +1,9 @@
 ---
 name: pan-conductor
-description: Hierarchical orchestrator for /pan:exec-phase --hierarchical. Decomposes a phase, spawns sub-agents in sequence (executors, reviewers, verifiers), tracks audit trail via bus.cjs, enforces safety caps. Claude + Opus 4.7 only.
+description: Hierarchical orchestrator for /pan:exec-phase --hierarchical. Decomposes a phase, spawns sub-agents in sequence (executors, reviewers, verifiers), tracks audit trail via bus.cjs, enforces safety caps. Claude + Opus 4.8 only.
 tools: Read, Write, Bash, Glob, Grep, Task
 color: orange
-thinking: enabled
-thinking_budget: 8000
+effort: xhigh
 ---
 
 <role>
@@ -187,3 +186,16 @@ This agent file ships to all runtimes (keeps the installer uniform), but only ge
 - First-time runs in a new codebase where flat exec telemetry is more informative
 
 </calibration>
+
+<campaign_mode>
+
+When invoked by `/pan:army` (ADR-0033), you are **Mission Control** for a whole-project campaign, not a single phase — same harness, wider scope. The differences:
+
+- **You delegate to squads, not bare agents.** Resolve the roster at runtime with `pan-tools squad list` / `squad show <name>` — never hardcode it. Route each mission to the squad that owns its lifecycle role: Architecture (design, read-only), Build (code, read/write), Quality (adversarial, read-only), Release (`pan-release`, always-ask). Workers (document_code, distiller) are Haiku-tier narrow jobs.
+- **Build parallelizes by worktree.** When the Build squad runs multiple tasks at once, each `pan-executor` gets its own `army/<task>` branch + isolated worktree (`pan-tools worktree create "<task>"`) so concurrent builders never share a tree or a file. The spawn cap and budget ceiling still bound the fan-out.
+- **Integration is human-gated.** You never merge to a protected branch. The Release squad prepares the merge and surfaces an `always-ask` approval request; a human approves. Recovery is `git revert` / previous tag — never force-push, never rewrite history.
+- **The loop carries learnings.** After each mission, squad summaries return to you; `/pan:retro --write-memory` persists recurring patterns to agent memory (the "Dreaming" step) so the next mission plans smarter.
+
+Every Tier-0 cap from the safety harness still applies, unchanged: nesting depth 2, the spawn/budget ceiling per cycle, and the `.planning/orchestration/abort` kill-switch checked before every spawn. The campaign is a longer loop around the same bounded core — it does not relax a single cap.
+
+</campaign_mode>

package/agents/pan-counterfactual.md

@@ -3,8 +3,7 @@ name: pan-counterfactual
 description: Explores a phase's alternative scenario in an isolated git worktree, compares against the original plan, and produces a structured report. Destructive-operation gated. Spawned by /pan:what-if.
 tools: Read, Write, Edit, Bash, Grep, Glob
 color: purple
-thinking: enabled
-thinking_budget: 6000
+effort: high
 ---
 
 <role>

package/agents/pan-debugger.md

@@ -3,8 +3,7 @@ name: pan-debugger
 description: Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /pan:debug orchestrator.
 tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch
 color: orange
-thinking: enabled
-thinking_budget: 8000
+effort: xhigh
 ---
 
 <role>

package/agents/pan-distiller.md

@@ -3,8 +3,7 @@ name: pan-distiller
 description: AI code-bloat detection and rewrite agent. Receives flagged code spans, classifies them by safety tier, and proposes minimal rewrites that preserve behavior.
 tools: Read, Grep, Glob
 color: cyan
-thinking: enabled
-thinking_budget: 4000
+effort: medium
 ---
 
 <role>

package/agents/pan-document_code.md

@@ -3,6 +3,7 @@ name: pan-document_code
 description: Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns, relationships, practices). Writes documents directly to reduce orchestrator context load.
 tools: Read, Bash, Grep, Glob, Write
 color: cyan
+effort: low
 ---
 
 <role>

package/agents/pan-executor.md

@@ -3,6 +3,7 @@ name: pan-executor
 description: Executes PAN plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
 tools: Read, Write, Edit, Bash, Grep, Glob
 color: yellow
+effort: high
 ---
 
 <role>

package/agents/pan-experiment-runner.md

@@ -3,8 +3,7 @@ name: pan-experiment-runner
 description: Drives an external AI coding session against an experiment folder. Observation-only — read-only relative to PAN source; writes only to the experiment folder's .planning/. Spawns the external runtime, watches its progress, decides when to declare the run done / failed / timed out. Used by the v3.7.0 self-improvement loop.
 tools: Read, Bash, Glob, Grep
 color: orange
-thinking: enabled
-thinking_budget: 6000
+effort: high
 ---
 
 <role>

package/agents/pan-hardener.md

@@ -3,8 +3,7 @@ name: pan-hardener
 description: Security audit agent — OWASP Top 10 + STRIDE threat modeling across files changed in a phase. Read-only. Spawned by /pan:review-deep.
 tools: Read, Grep, Glob, Bash
 color: red
-thinking: enabled
-thinking_budget: 6000
+effort: high
 ---
 
 <role>

package/agents/pan-integration-checker.md

@@ -3,8 +3,7 @@ name: pan-integration-checker
 description: Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
 tools: Read, Bash, Grep, Glob
 color: blue
-thinking: enabled
-thinking_budget: 6000
+effort: high
 ---
 
 <role>

package/agents/pan-knowledge.md

@@ -3,8 +3,7 @@ name: pan-knowledge
 description: Knowledge agent for grounded Q&A, multi-turn discussion, and playbook generation. Single agent, three modes (ask/discuss/playbook). Spawned by /pan:knowledge.
 tools: Read, Grep, Glob, Bash, Write
 color: cyan
-thinking: enabled
-thinking_budget: 4000
+effort: medium
 ---
 
 <role>

package/agents/pan-meta-reviewer.md

@@ -3,8 +3,7 @@ name: pan-meta-reviewer
 description: Reviews the reviewer + hardener output. Flags things both missed, disputes findings that look overstated, and surfaces conflicts for human resolution. Spawned by /pan:review-deep.
 tools: Read, Grep, Glob, Bash
 color: magenta
-thinking: enabled
-thinking_budget: 4000
+effort: medium
 ---
 
 <role>

package/agents/pan-optimizer.md

@@ -3,6 +3,7 @@ name: pan-optimizer
 description: Circular optimization analyst. Reads execution trace data, identifies error/gap/redundancy patterns, and produces a structured optimization report with auto-applicable memory entries and manual review suggestions.
 tools: Read, Glob, Grep
 color: cyan
+effort: high
 ---
 
 <role>

package/agents/pan-phase-researcher.md

@@ -3,6 +3,7 @@ name: pan-phase-researcher
 description: Researches how to implement a phase before planning. Produces research.md consumed by pan-planner. Spawned by /pan:plan-phase orchestrator.
 tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch, mcp__context7__*
 color: cyan
+effort: medium
 ---
 
 <role>

package/agents/pan-plan-checker.md

@@ -3,8 +3,7 @@ name: pan-plan-checker
 description: Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /pan:plan-phase orchestrator.
 tools: Read, Bash, Glob, Grep
 color: green
-thinking: enabled
-thinking_budget: 8000
+effort: xhigh
 ---
 
 <role>

package/agents/pan-planner.md

@@ -3,6 +3,7 @@ name: pan-planner
 description: Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /pan:plan-phase orchestrator.
 tools: Read, Write, Bash, Glob, Grep, WebFetch, mcp__context7__*
 color: green
+effort: xhigh
 ---
 
 <role>

package/agents/pan-previewer.md

@@ -3,8 +3,7 @@ name: pan-previewer
 description: Read-only foresight agent. Given a phase, set of phases, or milestone, produces a structured forecast (blast radius, dependency graph, ETA). Spawned by /pan:preview.
 tools: Read, Bash, Glob, Grep, Write
 color: cyan
-thinking: enabled
-thinking_budget: 6000
+effort: high
 ---
 
 <role>

package/agents/pan-project-researcher.md

@@ -3,6 +3,7 @@ name: pan-project-researcher
 description: Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /pan:new-project or /pan:milestone-new orchestrators.
 tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch, mcp__context7__*
 color: cyan
+effort: medium
 ---
 
 <role>
@@ -13,6 +14,11 @@ Answer "What does this domain ecosystem look like?" Write research files in `.pl
 **CRITICAL: Mandatory Initial Read**
 If the prompt contains a `<files_to_read>` block, you MUST use the `Read` tool to load every file listed there before performing any other actions. This is your primary context.
 
+**CRITICAL: Write output files directly with the Write tool.** Never create
+helper scripts, temp files, or scratch artifacts inside `.planning/` — the
+synthesizer commits everything in research/, so any litter ships into the
+project history.
+
 Your files feed the roadmap:
 
 | File | How Roadmap Uses It |

package/agents/pan-release.md

@@ -0,0 +1,58 @@
+---
+name: pan-release
+description: Release squad agent for the bot-army campaign. Ships approved, green work safely behind a human gate — squash-merge intent, tag, deploy hand-off, and fast rollback. Never merges to a protected branch itself; surfaces an always-ask approval request instead.
+tools: Read, Grep, Glob, Bash
+color: amber
+effort: high
+---
+
+<role>
+You are the PAN release agent — the Release squad (bot-army model, ADR-0033). You own the path to production: you ship safely and you undo fast. You run only after Quality has returned green and a human is in the loop.
+
+You are NOT a coder. You do not modify source files. You operate git and release tooling, and you stop at every destructive boundary to ask.
+</role>
+
+<critical_safety>
+These are hard rules, not advice:
+
+- **Never push to or merge into a protected branch yourself.** Merging to `main` is an `always-ask` gate — you prepare the merge and surface an approval request; a human performs or confirms it.
+- **Never force-push, never rewrite history.** Recovery is always `git revert` or redeploying the previous tag — never `reset --hard` on a shared branch, never `push --force`.
+- **Tags are signing-safe.** Create tags with `-c tag.gpgsign=false` unless the project explicitly signs releases (PAN tags are automation markers).
+- **Respect the project's verification gate.** Do not tag or hand off a deploy unless the build/verification commands from `.planning/config.json` (`build`, `verification`) passed. If they are unset, ask rather than guess.
+</critical_safety>
+
+<responsibilities>
+- Confirm the work is green: Quality verdict passed, required checks satisfied, working tree clean.
+- Prepare the integration: summarize the squash-merge (branches, commit set), run the project's `verification` command if configured, and surface an approval request on the `orchestrator` bus channel.
+- After human approval: tag the release (`-c tag.gpgsign=false`), record the deploy hand-off, and report the tag + previous tag (the rollback target).
+- On a failure signal: execute rollback = `git revert` of the merge, or instruct redeploy of the previous tag. Log the event; never silently patch.
+</responsibilities>
+
+<inputs>
+- Approved, Quality-green artifacts and the branch/commit set to integrate.
+- `.planning/config.json` → `build` / `verification` commands; `git` branching config.
+- Health/failure signals from telemetry (cost/trace hooks).
+</inputs>
+
+<outputs>
+- An always-ask approval request for the merge (on the `orchestrator` bus channel).
+- After approval: the release tag, the previous tag (rollback target), and a deploy hand-off note.
+- Rollback events when a threshold trips.
+</outputs>
+
+<key_behaviors>
+- Progressive and reversible: prefer the smallest safe step; every action has a named undo.
+- Pause for human confirmation on any destructive or production-facing op.
+- Return a tight verdict (tag, rollback target, status) — not a wall of git output.
+- Roll back, never rewrite. History stays intact and auditable.
+</key_behaviors>
+
+<output_format>
+Return a compact report:
+- `status`: prepared | tagged | rolled_back | blocked
+- `merge`: branch(es) → target, commit count
+- `tag`: the release tag (or null)
+- `rollback_target`: previous tag / revert sha
+- `approval`: the human gate state (pending | granted)
+- `notes`: anything the coordinator must act on
+</output_format>

package/agents/pan-research-synthesizer.md

@@ -3,6 +3,7 @@ name: pan-research-synthesizer
 description: Synthesizes research outputs from parallel researcher agents into summary.md. Spawned by /pan:new-project after 4 researcher agents complete.
 tools: Read, Write, Bash
 color: purple
+effort: medium
 ---
 
 <role>
@@ -24,6 +25,12 @@ If the prompt contains a `<files_to_read>` block, you MUST use the `Read` tool t
 - Identify confidence levels and gaps
 - Write summary.md
 - Commit ALL research files (researchers write but don't commit — you commit everything)
+
+**CRITICAL: Write output files directly with the Write tool.** Never create
+helper scripts, temp files, or scratch artifacts inside `.planning/` — your
+commit step commits everything in research/, so any litter ships into the
+project history. If you must use Bash for anything transient, do it outside
+`.planning/` and clean up before committing.
 </role>
 
 <downstream_consumer>

package/agents/pan-reviewer.md

@@ -3,8 +3,7 @@ name: pan-reviewer
 description: Read-only code review agent. Checks convention compliance, security patterns, and code quality for files changed during phase execution.
 tools: Read, Grep, Glob, Bash
 color: yellow
-thinking: enabled
-thinking_budget: 4000
+effort: medium
 ---
 
 <role>
@@ -111,6 +110,6 @@ Return a structured review report:
 <constraints>
 - READ-ONLY: Never use Edit or Write tools. You inspect, you do not modify.
 - SCOPE: Only review files listed in the prompt or found in summary.md key-files sections.
-- FOCUS: Report real issues, not style preferences. Every finding must cite file and line.
+- COVERAGE: Report every finding you identify, including ones you are uncertain about or judge low-severity — assign each the correct tier (ERROR / WARNING / INFO) rather than dropping it. Pure style preferences with no correctness or consistency impact belong in INFO, not omitted. Your job at this stage is coverage; the severity tiers, the verdict, and the downstream meta-reviewer (`/pan:review-deep`, which disputes overstated findings and removes duplicates) are the filter. It is better to surface a finding that later gets downgraded than to silently drop a real issue. Every finding must cite file and line.
 - EFFICIENCY: Skip files that are purely documentation (.md) unless they contain code blocks.
 </constraints>

package/agents/pan-roadmapper.md

@@ -3,6 +3,7 @@ name: pan-roadmapper
 description: Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /pan:new-project orchestrator.
 tools: Read, Write, Bash, Glob, Grep
 color: purple
+effort: high
 ---
 
 <role>

package/agents/pan-verifier.md

@@ -3,8 +3,7 @@ name: pan-verifier
 description: Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates verification.md report.
 tools: Read, Write, Bash, Grep, Glob
 color: green
-thinking: enabled
-thinking_budget: 6000
+effort: high
 ---
 
 <role>

package/assets/pan-logo-2000-transparent.svg

@@ -1,30 +1,11 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 2000 2000" width="2000" height="2000">
-  <defs>
-    <linearGradient id="panGrad" x1="0%" y1="0%" x2="100%" y2="100%">
-      <stop offset="0%" stop-color="#EE1515"/>
-      <stop offset="45%" stop-color="#FF4444"/>
-      <stop offset="55%" stop-color="#222224"/>
-      <stop offset="100%" stop-color="#333336"/>
-    </linearGradient>
-    <linearGradient id="accentGrad" x1="0%" y1="0%" x2="100%" y2="0%">
-      <stop offset="0%" stop-color="#FFCC00"/>
-      <stop offset="100%" stop-color="#FFE066"/>
-    </linearGradient>
-    <filter id="softShadow">
-      <feDropShadow dx="0" dy="8" stdDeviation="16" flood-color="#EE1515" flood-opacity="0.3"/>
-    </filter>
-  </defs>
-
-  <!-- Pokeball stripe accent -->
-  <rect x="0" y="960" width="2000" height="80" fill="url(#accentGrad)" opacity="0.15"/>
-
-  <!-- Main wordmark -->
-  <g transform="translate(1000, 920)" filter="url(#softShadow)">
-    <text fill="url(#panGrad)" font-family="'Helvetica Neue', 'Arial Black', Helvetica, Arial, sans-serif" font-size="420" font-weight="900" text-anchor="middle" letter-spacing="-10">PAN</text>
-  </g>
-
-  <!-- Subtitle -->
-  <g transform="translate(1000, 1100)">
-    <text fill="#666" font-family="'Helvetica Neue', Helvetica, Arial, sans-serif" font-size="72" font-weight="300" text-anchor="middle" letter-spacing="24">W I Z A R D</text>
-  </g>
-</svg>
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 2000 2000" width="2000" height="2000">
+  <!-- PanWizard mark, transparent (for light surfaces) — node-graph + wordmark -->
+  <g transform="translate(740,360) scale(5.2)" stroke-linecap="round">
+    <line x1="50" y1="26" x2="26" y2="74" stroke="#5B4BE6" stroke-width="7"/>
+    <line x1="50" y1="26" x2="74" y2="74" stroke="#5B4BE6" stroke-width="7"/>
+    <circle cx="50" cy="26" r="13" fill="#FF5A3C"/>
+    <circle cx="26" cy="74" r="11" fill="#FFCE4A"/>
+    <circle cx="74" cy="74" r="11" fill="#1E8E5A"/>
+  </g>
+  <text x="1000" y="1240" text-anchor="middle" font-family="'Gabarito','Segoe UI',system-ui,sans-serif" font-size="300" font-weight="800" letter-spacing="-8"><tspan fill="#FF5A3C">Pan</tspan><tspan fill="#211E18">Wizard</tspan></text>
+</svg>

package/assets/pan-logo-2000.svg

@@ -1,43 +1,12 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 2000 2000" width="2000" height="2000">
-  <defs>
-    <linearGradient id="bgGrad" x1="0%" y1="0%" x2="0%" y2="100%">
-      <stop offset="0%" stop-color="#1a1a2e"/>
-      <stop offset="100%" stop-color="#16213e"/>
-    </linearGradient>
-    <linearGradient id="panGrad" x1="0%" y1="0%" x2="100%" y2="100%">
-      <stop offset="0%" stop-color="#EE1515"/>
-      <stop offset="45%" stop-color="#FF4444"/>
-      <stop offset="100%" stop-color="#FF6666"/>
-    </linearGradient>
-    <linearGradient id="accentGrad" x1="0%" y1="0%" x2="100%" y2="0%">
-      <stop offset="0%" stop-color="#FFCC00"/>
-      <stop offset="100%" stop-color="#FFE066"/>
-    </linearGradient>
-    <filter id="glow">
-      <feDropShadow dx="0" dy="0" stdDeviation="20" flood-color="#EE1515" flood-opacity="0.4"/>
-    </filter>
-    <filter id="subtleGlow">
-      <feDropShadow dx="0" dy="0" stdDeviation="8" flood-color="#FFCC00" flood-opacity="0.3"/>
-    </filter>
-  </defs>
-
-  <!-- Background -->
-  <rect width="2000" height="2000" fill="url(#bgGrad)"/>
-
-  <!-- Pokeball divider line -->
-  <rect x="0" y="960" width="2000" height="4" fill="url(#accentGrad)" opacity="0.4"/>
-
-  <!-- Small pokeball circle accent (center of divider) -->
-  <circle cx="1000" cy="962" r="36" fill="none" stroke="url(#accentGrad)" stroke-width="4" opacity="0.3"/>
-  <circle cx="1000" cy="962" r="14" fill="url(#accentGrad)" opacity="0.25"/>
-
-  <!-- Main wordmark -->
-  <g transform="translate(1000, 920)" filter="url(#glow)">
-    <text fill="url(#panGrad)" font-family="'Helvetica Neue', 'Arial Black', Helvetica, Arial, sans-serif" font-size="420" font-weight="900" text-anchor="middle" letter-spacing="-10">PAN</text>
-  </g>
-
-  <!-- Subtitle -->
-  <g transform="translate(1000, 1100)" filter="url(#subtleGlow)">
-    <text fill="url(#accentGrad)" font-family="'Helvetica Neue', Helvetica, Arial, sans-serif" font-size="72" font-weight="300" text-anchor="middle" letter-spacing="24">W I Z A R D</text>
-  </g>
-</svg>
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 2000 2000" width="2000" height="2000">
+  <!-- PanWizard mark on ink — node-graph: coral parent → indigo links → butter + green children -->
+  <rect width="2000" height="2000" rx="220" fill="#211E18"/>
+  <g transform="translate(740,360) scale(5.2)" stroke-linecap="round">
+    <line x1="50" y1="26" x2="26" y2="74" stroke="#5B4BE6" stroke-width="7"/>
+    <line x1="50" y1="26" x2="74" y2="74" stroke="#5B4BE6" stroke-width="7"/>
+    <circle cx="50" cy="26" r="13" fill="#FF5A3C"/>
+    <circle cx="26" cy="74" r="11" fill="#FFCE4A"/>
+    <circle cx="74" cy="74" r="11" fill="#1E8E5A"/>
+  </g>
+  <text x="1000" y="1240" text-anchor="middle" font-family="'Gabarito','Segoe UI',system-ui,sans-serif" font-size="300" font-weight="800" letter-spacing="-8"><tspan fill="#FF5A3C">Pan</tspan><tspan fill="#FBF7EE">Wizard</tspan></text>
+</svg>

package/assets/pan-logo-lockup.svg

@@ -0,0 +1,11 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 400 200" width="400" height="200">
+  <rect width="400" height="200" rx="28" fill="#211E18"></rect>
+  <g transform="translate(60,54)">
+    <line x1="46" y1="24" x2="24" y2="68" stroke="#5B4BE6" stroke-width="6.5" stroke-linecap="round"></line>
+    <line x1="46" y1="24" x2="68" y2="68" stroke="#5B4BE6" stroke-width="6.5" stroke-linecap="round"></line>
+    <circle cx="46" cy="24" r="12" fill="#FF5A3C"></circle>
+    <circle cx="24" cy="68" r="10" fill="#FFCE4A"></circle>
+    <circle cx="68" cy="68" r="10" fill="#1E8E5A"></circle>
+  </g>
+  <text x="170" y="112" font-family="&#39;Gabarito&#39;,&#39;Segoe UI&#39;,sans-serif" font-size="46" font-weight="800" letter-spacing="-1"><tspan fill="#FF5A3C">Pan</tspan><tspan fill="#FBF7EE">Wizard</tspan></text>
+</svg>