@selesai/code 0.9.11 → 0.9.12

package/dist/skills/industrial-brutalist-ui/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: industrial-brutalist-ui
+description: Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
+license: MIT
+---
+
+# SKILL: Industrial Brutalism & Tactical Telemetry UI
+
+## 1. Skill Meta
+**Name:** Industrial Brutalism & Tactical Telemetry Interface Engineering
+**Description:** Advanced proficiency in architecting web interfaces that synthesize mid-century Swiss Typographic design, industrial manufacturing manuals, and retro-futuristic aerospace/military terminal interfaces. This discipline requires absolute mastery over rigid modular grids, extreme typographic scale contrast, purely utilitarian color palettes, and the programmatic simulation of analog degradation (halftones, CRT scanlines, bitmap dithering). The objective is to construct digital environments that project raw functionality, mechanical precision, and high data density, deliberately discarding conventional consumer UI patterns.
+
+## 2. Visual Archetypes
+The design system operates by merging two distinct but highly compatible visual paradigms. **Pick ONE per project and commit to it. Do not alternate or mix both modes within the same interface.**
+
+### 2.1 Swiss Industrial Print
+Derived from 1960s corporate identity systems and heavy machinery blueprints.
+*   **Characteristics:** High-contrast light modes (newsprint/off-white substrates). Reliance on monolithic, heavy sans-serif typography. Unforgiving structural grids outlined by visible dividing lines. Aggressive, asymmetric use of negative space punctuated by oversized, viewport-bleeding numerals or letterforms. Heavy use of primary red as an alert/accent color.
+
+### 2.2 Tactical Telemetry & CRT Terminal
+Derived from classified military databases, legacy mainframes, and aerospace Heads-Up Displays (HUDs).
+*   **Characteristics:** Dark mode exclusivity. High-density tabular data presentation. Absolute dominance of monospaced typography. Integration of technical framing devices (ASCII brackets, crosshairs). Application of simulated hardware limitations (phosphor glow, scanlines, low bit-depth rendering).
+
+## 3. Typographic Architecture
+Typography is the primary structural and decorative infrastructure. Imagery is secondary. The system demands extreme variance in scale, weight, and spacing.
+
+### 3.1 Macro-Typography (Structural Headers)
+*   **Classification:** Neo-Grotesque / Heavy Sans-Serif.
+*   **Optimal Web Fonts:** Neue Haas Grotesk (Black), Inter (Extra Bold/Black), Archivo Black, Roboto Flex (Heavy), Monument Extended.
+*   **Implementation Parameters:**
+    *   **Scale:** Deployed at massive scales using fluid typography (e.g., `clamp(4rem, 10vw, 15rem)`).
+    *   **Tracking (Letter-spacing):** Extremely tight, often negative (`-0.03em` to `-0.06em`), forcing glyphs to form solid architectural blocks.
+    *   **Leading (Line-height):** Highly compressed (`0.85` to `0.95`).
+    *   **Casing:** Exclusively uppercase for structural impact.
+
+### 3.2 Micro-Typography (Data & Telemetry)
+*   **Classification:** Monospace / Technical Sans.
+*   **Optimal Web Fonts:** JetBrains Mono, IBM Plex Mono, Space Mono, VT323, Courier Prime.
+*   **Implementation Parameters:**
+    *   **Scale:** Fixed and small (`10px` to `14px` / `0.7rem` to `0.875rem`).
+    *   **Tracking:** Generous (`0.05em` to `0.1em`) to simulate mechanical typewriter spacing or terminal matrices.
+    *   **Leading:** Standard to tight (`1.2` to `1.4`).
+    *   **Casing:** Exclusively uppercase. Used for all metadata, navigation, unit IDs, and coordinates.
+
+### 3.3 Textural Contrast (Artistic Disruption)
+*   **Classification:** High-Contrast Serif.
+*   **Optimal Web Fonts:** Playfair Display, EB Garamond, Times New Roman.
+*   **Implementation Parameters:** Used exceedingly sparingly. Must be subjected to heavy post-processing (halftone filters, 1-bit dithering) to degrade vector perfection and create textural juxtaposition against the clean sans-serifs.
+
+## 4. Color System
+The color architecture is uncompromising. Gradients, soft drop shadows, and modern translucency are strictly prohibited. Colors simulate physical media or primitive emissive displays.
+
+**CRITICAL: Choose ONE substrate palette per project and use it consistently. Never mix light and dark substrates within the same interface.**
+
+### If Swiss Industrial Print (Light):
+*   **Background:** `#F4F4F0` or `#EAE8E3` (Matte, unbleached documentation paper).
+*   **Foreground:** `#050505` to `#111111` (Carbon Ink).
+*   **Accent:** `#E61919` or `#FF2A2A` (Aviation/Hazard Red). This is the ONLY accent color. Used for strike-throughs, thick structural dividing lines, or vital data highlights.
+
+### If Tactical Telemetry (Dark):
+*   **Background:** `#0A0A0A` or `#121212` (Deactivated CRT. Avoid pure `#000000`).
+*   **Foreground:** `#EAEAEA` (White phosphor). This is the primary text color.
+*   **Accent:** `#E61919` or `#FF2A2A` (Aviation/Hazard Red). Same red, same rules.
+*   **Terminal Green (`#4AF626`):** Optional. Use ONLY for a single specific UI element (e.g., one status indicator or one data readout) — never as a general text color. If it doesn't serve a clear purpose, omit it entirely.
+
+## 5. Layout and Spatial Engineering
+The layout must appear mathematically engineered. It rejects conventional web padding in favor of visible compartmentalization.
+
+*   **The Blueprint Grid:** Strict adherence to CSS Grid architectures. Elements do not float; they are anchored precisely to grid tracks and intersections.
+*   **Visible Compartmentalization:** Extensive utilization of solid borders (`1px` or `2px solid`) to delineate distinct zones of information. Horizontal rules (`<hr>`) frequently span the entire container width to segregate operational units.
+*   **Bimodal Density:** Layouts oscillate between extreme data density (tightly packed monospace metadata clustered together) and vast expanses of calculated negative space framing macro-typography.
+*   **Geometry:** Absolute rejection of `border-radius`. All corners must be exactly 90 degrees to enforce mechanical rigidity.
+
+## 6. UI Components and Symbology
+Standard web UI conventions are replaced with utilitarian, industrial graphic elements.
+
+*   **Syntax Decoration:** Utilization of ASCII characters to frame data points.
+    *   *Framing:* `[ DELIVERY SYSTEMS ]`, `< RE-IND >`
+    *   *Directional:* `>>>`, `///`, `\\\\`
+*   **Industrial Markers:** Prominent integration of registration (`®`), copyright (`©`), and trademark (`™`) symbols functioning as structural geometric elements rather than legal text.
+*   **Technical Assets:** Integration of crosshairs (`+`) at grid intersections, repeating vertical lines (barcodes), thick horizontal warning stripes, and randomized string data (e.g., `REV 2.6`, `UNIT / D-01`) to simulate active mechanical processes.
+
+## 7. Textural and Post-Processing Effects
+To prevent the design from appearing purely digital, simulated analog degradation is engineered into the frontend via CSS and SVG filters.
+
+*   **Halftone and 1-Bit Dithering:** Transforming continuous-tone images or large serif typography into dot-matrix patterns. Achieved via pre-processing or CSS `mix-blend-mode: multiply` overlays combined with SVG radial dot patterns.
+*   **CRT Scanlines:** For terminal interfaces, applying a `repeating-linear-gradient` to the background to simulate horizontal electron beam sweeps (e.g., `repeating-linear-gradient(0deg, transparent, transparent 2px, rgba(0,0,0,0.1) 2px, rgba(0,0,0,0.1) 4px)`).
+*   **Mechanical Noise:** A global, low-opacity SVG static/noise filter applied to the DOM root to introduce a unified physical grain across both dark and light modes.
+
+## 8. Web Engineering Directives
+1.  **Grid Determinism:** Utilize `display: grid; gap: 1px;` with contrasting parent/child background colors to generate mathematically perfect, razor-thin dividing lines without complex border declarations.
+2.  **Semantic Rigidity:** Construct the DOM using precise semantic tags (`<data>`, `<samp>`, `<kbd>`, `<output>`, `<dl>`) to accurately reflect the technical nature of the telemetry.
+3.  **Typography Clamping:** Implement CSS `clamp()` functions exclusively for macro-typography to ensure massive text scales aggressively while maintaining structural integrity across viewports.

package/dist/skills/minimalist-ui/SKILL.md

@@ -0,0 +1,86 @@
+---
+name: minimalist-ui
+description: Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
+license: MIT
+---
+
+# Protocol: Premium Utilitarian Minimalism UI Architect
+
+## 1. Protocol Overview
+Name: Premium Utilitarian Minimalism & Editorial UI
+Description: An advanced frontend engineering directive for generating highly refined, ultra-minimalist, "document-style" web interfaces analogous to top-tier workspace platforms. This protocol strictly enforces a high-contrast warm monochrome palette, bespoke typographic hierarchies, meticulous structural macro-whitespace, bento-grid layouts, and an ultra-flat component architecture with deliberate muted pastel accents. It actively rejects standard generic SaaS design trends.
+
+## 2. Absolute Negative Constraints (Banned Elements)
+The AI must strictly avoid the following generic web development defaults:
+- DO NOT use the "Inter", "Roboto", or "Open Sans" typefaces.
+- DO NOT use generic, thin-line icon libraries like "Lucide", "Feather", or standard "Heroicons".
+- DO NOT use Tailwind's default heavy drop shadows (e.g., `shadow-md`, `shadow-lg`, `shadow-xl`). Shadows must be practically non-existent or heavily customized to be ultra-diffuse and low opacity (< 0.05).
+- DO NOT use primary colored backgrounds for large elements or sections (e.g., no bright blue, green, or red hero sections).
+- DO NOT use gradients, neon colors, or 3D glassmorphism (beyond subtle navbar blurs).
+- DO NOT use `rounded-full` (pill shapes) for large containers, cards, or primary buttons.
+- DO NOT use emojis anywhere in code, markup, text content, headings, or alt text. Replace with proper icons or clean SVG primitives.
+- DO NOT use generic placeholder names like "John Doe", "Acme Corp", or "Lorem Ipsum". Use realistic, contextual content.
+- DO NOT use AI copywriting clichés: "Elevate", "Seamless", "Unleash", "Next-Gen", "Game-changer", "Delve". Write plain, specific language.
+
+## 3. Typographic Architecture
+The interface must rely on extreme typographic contrast and premium font selection to establish an editorial feel.
+- Primary Sans-Serif (Body, UI, Buttons): Use clean, geometric, or system-native fonts with character. Target: `font-family: 'SF Pro Display', 'Geist Sans', 'Helvetica Neue', 'Switzer', sans-serif`.
+- Editorial Serif (Hero Headings & Quotes): Target: `font-family: 'Lyon Text', 'Newsreader', 'Playfair Display', 'Instrument Serif', serif`. Apply tight tracking (`letter-spacing: -0.02em` to `-0.04em`) and tight line-height (`1.1`).
+- Monospace (Code, Keystrokes, Meta-data): Target: `font-family: 'Geist Mono', 'SF Mono', 'JetBrains Mono', monospace`.
+- Text Colors: Body text must never be absolute black (`#000000`). Use off-black/charcoal (`#111111` or `#2F3437`) with a generous `line-height` of `1.6` for legibility. Secondary text should be muted gray (`#787774`).
+
+## 4. Color Palette (Warm Monochrome + Spot Pastels)
+Color is a scarce resource, utilized only for semantic meaning or subtle accents.
+- Canvas / Background: Pure White `#FFFFFF` or Warm Bone/Off-White `#F7F6F3` / `#FBFBFA`.
+- Primary Surface (Cards): `#FFFFFF` or `#F9F9F8`.
+- Structural Borders / Dividers: Ultra-light gray `#EAEAEA` or `rgba(0,0,0,0.06)`.
+- Accent Colors: Exclusively use highly desaturated, washed-out pastels for tags, inline code backgrounds, or subtle icon backgrounds.
+  - Pale Red: `#FDEBEC` (Text: `#9F2F2D`)
+  - Pale Blue: `#E1F3FE` (Text: `#1F6C9F`)
+  - Pale Green: `#EDF3EC` (Text: `#346538`)
+  - Pale Yellow: `#FBF3DB` (Text: `#956400`)
+
+## 5. Component Specifications
+- Bento Box Feature Grids:
+  - Utilize asymmetrical CSS Grid layouts.
+  - Cards must have exactly `border: 1px solid #EAEAEA`.
+  - Border-radius must be crisp: `8px` or `12px` maximum.
+  - Internal padding must be generous (e.g., `24px` to `40px`).
+- Primary Call-To-Action (Buttons):
+  - Solid background `#111111`, text `#FFFFFF`. 
+  - Slight border-radius (`4px` to `6px`). No box-shadow. 
+  - Hover state should be a subtle color shift to `#333333` or a micro-scale `transform: scale(0.98)`.
+- Tags & Status Badges:
+  - Pill-shaped (`border-radius: 9999px`), very small typography (`text-xs`), uppercase with wide tracking (`letter-spacing: 0.05em`).
+  - Background must use the defined Muted Pastels.
+- Accordions (FAQ):
+  - Strip all container boxes. Separate items only with a `border-bottom: 1px solid #EAEAEA`.
+  - Use a clean, sharp `+` and `-` icon for the toggle state.
+- Keystroke Micro-UIs:
+  - Render shortcuts as physical keys using `<kbd>` tags: `border: 1px solid #EAEAEA`, `border-radius: 4px`, `background: #F7F6F3`, using the Monospace font.
+- Faux-OS Window Chrome:
+  - When mocking up software, wrap it in a minimalist container with a white top bar containing three small, light gray circles (replicating macOS window controls).
+
+## 6. Iconography & Imagery Directives
+- System Icons: Use "Phosphor Icons (Bold or Fill weights)" or "Radix UI Icons" for a technical, slightly thicker-stroke aesthetic. Standardize stroke width across all icons.
+- Illustrations: Monochromatic, rough continuous-line ink sketches on a white background, featuring a single offset geometric shape filled with a muted pastel color.
+- Photography: Use high-quality, desaturated images with a warm tone. Apply subtle overlays (`opacity: 0.04` warm grain) to blend photos into the monochrome palette. Never use oversaturated stock photos. Use reliable placeholders like `https://picsum.photos/seed/{context}/1200/800` when real assets are unavailable.
+- Hero & Section Backgrounds: Sections should not feel empty and flat. Use subtle full-width background imagery at very low opacity, soft radial light spots (`radial-gradient` with warm tones at `opacity: 0.03`), or minimal geometric line patterns to add depth without breaking the clean aesthetic.
+
+## 7. Subtle Motion & Micro-Animations
+Motion should feel invisible — present but never distracting. The goal is quiet sophistication, not spectacle.
+- Scroll Entry: Elements fade in gently as they enter the viewport. Use `translateY(12px)` + `opacity: 0` resolving over `600ms` with `cubic-bezier(0.16, 1, 0.3, 1)`. Use `IntersectionObserver`, never `window.addEventListener('scroll')`.
+- Hover States: Cards lift with an ultra-subtle shadow shift (`box-shadow` transitioning from `0 0 0` to `0 2px 8px rgba(0,0,0,0.04)` over `200ms`). Buttons respond with `scale(0.98)` on `:active`.
+- Staggered Reveals: Lists and grid items enter with a cascade delay (`animation-delay: calc(var(--index) * 80ms)`). Never mount everything at once.
+- Background Ambient Motion: Optional. A single, very slow-moving radial gradient blob (`animation-duration: 20s+`, `opacity: 0.02-0.04`) drifting behind hero sections. Must be applied to a `position: fixed; pointer-events: none` layer. Never on scrolling containers.
+- Performance: Animate exclusively via `transform` and `opacity`. No layout-triggering properties (`top`, `left`, `width`, `height`). Use `will-change: transform` sparingly and only on actively animating elements.
+
+## 8. Execution Protocol
+When tasked with writing frontend code (HTML, React, Tailwind, Vue) or designing a layout:
+1. Establish the macro-whitespace first. Use massive vertical padding between sections (e.g., `py-24` or `py-32` in Tailwind).
+2. Constrain the main typography content width to `max-w-4xl` or `max-w-5xl`.
+3. Apply the custom typographic hierarchy and monochromatic color variables immediately.
+4. Ensure every card, divider, and border adheres strictly to the `1px solid #EAEAEA` rule.
+5. Add scroll-entry animations to all major content blocks.
+6. Ensure sections have visual depth through imagery, ambient gradients, or subtle textures — no empty flat backgrounds.
+7. Provide code that reflects this high-end, uncluttered, editorial aesthetic natively without requiring manual adjustments.

package/dist/skills/pi-subagents/SKILL.md

@@ -1,25 +1,20 @@
 ---
 name: pi-subagents
 description: |
-  Delegate work to builtin or custom subagents with single-agent, chain,
-  parallel, scripted, async, forked-context, mission-backed, and
-  intercom-coordinated workflows. Use for advisory review, implementation
-  handoffs, and multi-step tasks where a single agent stays in control while
-  other agents contribute context, planning, or execution.
+  Delegate work to builtin or custom subagents with single-agent, parallel,
+  scripted-chaining, async, forked-context, and coordinated workflows. Use
+  for advisory review, implementation handoffs, and multi-step tasks where a
+  single agent should stay in control while other agents contribute context,
+  planning, or execution.
 ---
 
-# Selesai Subagents
+# Pi Subagents
 
 This skill is for the main parent orchestrator only. Do not inject or follow it inside spawned child subagents. The parent session owns delegation, orchestration, review fanout, and final fix-worker launches. Ordinary children should not run their own subagent workflows; the explicit exception is a delegated fanout child whose resolved builtin `tools` includes `subagent`, and that child may use `subagent` only for the fanout work the parent assigned.
 
-Use this skill when the parent orchestrator needs one specialized child or composed orchestration. The `subagent` tool has four first-class execution modes:
+Use this skill when the parent orchestrator needs one specialized child or composed orchestration. Use `workflowScript` for all execution, including one isolated child. Chaining is still supported, but it is code-driven: use `await runs.run(...)` for sequential steps, `runs.all([...])` for parallel fanout, and ordinary JavaScript for branching, retries, gate monitors, and aggregation. Keep workflow helpers portable: use plain helper functions or explicit Promise chains, not nested `async function` helpers, async arrows, or async methods. Do not use legacy top-level `chain` / `tasks` inputs or durable `.chain.md` execution. Scripted workflows normally start asynchronously unless config sets `asyncByDefault:false`; set `async:true` explicitly when async behavior matters. Pass `async:false` only when the parent must block until completion. Async mode still shows progress. Do not use `async:false` for final reviews, backlog gates, run-to-completion convenience, or because no other work is available.
 
-- **SINGLE** — `{ agent, task }` for one child (omit `task` for a self-contained agent).
-- **CHAIN** — `{ chain: [{ agent, task }, ...] }` for sequential steps with `{previous}`, `{outputs.name}`, `phase`/`label`, `outputSchema`, and `{ checkpoint: "name" }` human gates.
-- **PARALLEL** — `{ tasks: [{ agent, task }, ...], concurrency? }` for top-level parallel children, plus in-chain `{ parallel: [...] }` groups and dynamic `expand`/`collect` fanout.
-- **SCRIPTED WORKFLOW** — `{ workflowScript }` with `runs.run`/`runs.all` and ordinary JavaScript for sequence, parallelism, branching, retries, gate monitors, and aggregation. Use `return runs.run("main", { agent, task })` for one child and `runs.all([...])` for coordinated waves. Scripts start asynchronously by default; pass `async:false` only for a small foreground run.
-
-Prefer the declarative modes when the shape is known up front; reach for `workflowScript` when coordination needs dynamic branching or aggregation. Saved `.chain.md` / `.chain.json` workflows (run with `/run-chain`) make repeatable multi-agent flows shareable without rewriting the chain each time.
+Package-installed agents appear in `subagent({ action: "list" })` with builtin, user, and project agents. If `surf-cli` is installed as a Pi package, the Surf browser extension is loaded, and Chrome is logged into a ChatGPT Pro account, Surf can expose `gpt-pro`: a read-only async advisor that reaches ChatGPT web through Surf Oracle. Check it with `subagent({ action: "get", agent: "gpt-pro" })` and run it with `subagent({ agent: "gpt-pro", task: "Review this plan and identify release risks." })`.
 
 ## How to use this router
 
@@ -28,8 +23,10 @@ Read the matching reference file before acting. Paths are relative to this `SKIL
 | Task | Read |
 | --- | --- |
 | Decide whether to delegate, choose agents, compare tool versus slash commands, apply prompt techniques, or understand builtin roles | `references/prompting-and-roles.md` |
-| Run single, chain, parallel, scripted, async, scheduled, mission-backed, forked, worktree, watchdog, clarify, oracle, or intercom-coordinated workflows | `references/execution-controls.md` |
-| List/create/update/delete/eject/disable agents or chains, edit agent files, use prompt-template integration, or expose extension RPC | `references/management-authoring-rpc.md` |
+| Use council mode, convene several advisors, debate a decision, cross-examine recommendations, critique or improve a plan with multiple model perspectives, or run `/council` | `../council-mode/SKILL.md` |
+| Run one-child, scripted, async, scheduled, mission-backed, forked, watchdog, oracle, or intercom-coordinated workflows | `references/execution-controls.md` |
+| Coordinate several independent tasks, worktrees, repositories, or writer lanes | `references/multi-lane-orchestration.md` |
+| List/create/update/delete/eject/disable agents, inspect legacy chain records, edit agent files, use prompt-template integration, or expose extension RPC | `references/management-authoring-rpc.md` |
 | Check safety constraints, best practices, standard workflows, or error handling | `references/constraints-and-recipes.md` |
 
 For broad or uncertain requests, read more than one reference. For complex work, start with `references/prompting-and-roles.md` and `references/execution-controls.md`, then consult `references/constraints-and-recipes.md` before launching or reviewing child work.
@@ -37,11 +34,15 @@ For broad or uncertain requests, read more than one reference. For complex work,
 ## Always-on constraints
 
 - Keep the parent as orchestrator and final decision-maker.
+- Before multiple mutation-capable lanes, record a lane board and each lane's isolation path.
+- For plan, design, or architecture advice that asks for council mode, asks to convene several advisors, compare model perspectives, debate a decision, cross-examine recommendations, or critique and improve a plan, read `../council-mode/SKILL.md` and use Council Mode instead of ad hoc parallel oracle calls.
+- For plan, design, or architecture advice that asks to consult, discuss with, or come to agreement with one `oracle`, use a short same-session consultation loop: read the first result, resume once with a targeted challenge when material tradeoffs remain, then synthesize the parent decision. Keep explicit one-shot, trivial, and fully settled consultations one-shot.
 - Use one writer per cwd/worktree unless isolated worktrees are intentional.
 - For cross-codebase work, record the target repo, explicit `cwd`, authority boundary, and expected output before launch. Do not assume the parent session cwd is the child repo.
-- For parallel fanout, compare child prompts before launch. Do not send clone prompts with only issue numbers, titles, or broad file globs swapped; each child needs a lane-specific task, source seam, prior evidence, and decision that remains distinct without the item number. Launch that fanout as one async `workflowScript` or parallel `tasks` group with stable keys and aggregate output unless there is truly only one child.
+- For parallel fanout, compare child prompts before launch. Do not send clone prompts with only issue numbers, titles, or broad file globs swapped; each child needs a lane-specific task, source seam, prior evidence, and decision that remains distinct without the item number. Launch that fanout as one async `workflowScript` with stable keys and aggregate output unless there is truly only one child.
 - Prefer fresh-context review/validation fanout, then synthesize and apply fixes in the parent.
-- Use async/background by default when work can proceed independently; do not poll just to wait. For planned human gates, use `{ checkpoint: "name", message?: "..." }` chain steps and approve or reject paused checkpoints with `approve-checkpoint` / `reject-checkpoint`. For adaptive gates, branch in `workflowScript`.
+- Use async/background by default. Final reviews, gate checks, oracle checks, and backlog lanes stay async. Use `async:false` only when the parent must block until completion. Do not poll just to wait. For adaptive gates, branch in `workflowScript`.
+- For Pi extension repos whose canonical checkout is under `~/.selesai/agent/extensions`, never create lane worktrees as sibling directories there. Pi auto-loads `~/.selesai/agent/extensions/*/index.ts`, so sibling worktrees can register duplicate tools. Put lanes under `~/.selesai/agent/worktrees`, another worktree base outside auto-discovery, or a temporary clone. If a lane must run the modified extension itself, use an isolated Pi config home with `SELESAI_CODING_AGENT_DIR=<lane-config> pi --no-extensions -e <lane>/index.ts`. Use full containers only when path and config isolation are insufficient.
 - Preserve capability ceilings, including child tool restrictions and session-scoped allowed-agent restrictions.
 - Escalate unresolved product, architecture, authority, release, merge, or safety decisions upward instead of letting a child decide silently.
 - Treat receipts, CI, review bots, and external-run records as evidence, not authority to merge, close, comment, publish, or release.

package/dist/skills/pi-subagents/references/constraints-and-recipes.md

@@ -1,13 +1,15 @@
-# Selesai Subagents: Constraints And Recipes
+# Pi Subagents: Constraints And Recipes
 
 This file is a detailed reference loaded from `skills/pi-subagents/SKILL.md`.
 
 ## Important Constraints
 
-- **Forking requires a persisted parent session.** If the current session does not
-  have a persisted session file, forked runs fail. Packaged `worker`, `oracle`,
-  and `advisor` default to forked context, so use `context: "fresh"` explicitly
-  when that is not available or not wanted.
+- **Explicit forking requires a persisted parent session.** If the current session
+  does not have a persisted session file or current leaf, explicit `context: "fork"`
+  fails. An agent-level `defaultContext: fork` is a preference: packaged `worker`,
+  `oracle`, and `advisor` fall back to `fresh` when those fork preconditions are not
+  met yet. Use `context: "fresh"` when you do not want a fork even after the parent
+  session exists.
 - **Forked runs inherit parent history.** They are branched threads, not fresh
   filtered contexts. Use fresh context for adversarial reviewers unless the user explicitly asks for forked context.
 - **Default subagent nesting depth is 2.** Deeper recursive delegation is blocked
@@ -19,7 +21,13 @@ This file is a detailed reference loaded from `skills/pi-subagents/SKILL.md`.
   become second decision-makers.
 - **Respect the fixed authority policy.** `authorityPolicy` is a small `auto` / `confirm` / `forbid` map for supported operational actions. Worktree discard, destructive cleanup, and spawn-budget grants default to confirmation; stop, steer, and schedule creation remain automatic. Use `worktree.discard` with the durable `handoffPath`; confirm-required actions refuse safely without an interactive UI and retained paths include manual Git recovery commands.
 
-Runtime config can change orchestration behavior. `intercomBridge.resultDelivery: false` disables only external acknowledged grouped-result delivery when native parent notifications own completion; supervisor asks/progress stay active, and enabled transport failures are still reported. `asyncByDefault` and `forceTopLevelAsync` affect whether launches detach; `waitTool` can make direct `subagent_wait()` calls return immediately while headless auto-drain remains active, and its effective value is propagated to child runtimes; `globalConcurrencyLimit` bounds concurrent fanout, while a positive `maxSubagentSpawnsPerSession` optionally caps cumulative launches (`0` or unset is unlimited). Status and doctor report the budget; static work preflights declared capacity; only the settled root interactive parent can use `grant-spawn-budget` after native confirmation, with total grants bounded by the original cap. Compaction does not reset usage or grants; `singleRunOutputBaseDir` and `worktreeBaseDir` route outputs and worktrees; `completionBatch` groups async notifications. `artifactDir` is `project` (default), `session`, or `temp` and chooses where subagent artifacts are stored. Set `asyncWidget: false` to hide the above-editor background-run widget when a companion footer or dashboard owns that space (run status view remains available). Per-run `artifacts: false` disables artifact capture for that launch. Async status and result artifacts include `lifecycleArtifactVersion` and fields such as `workflowGraph`, `steps`, `results`, `totalTokens`, `totalCost`, `turnCount`, `toolCount`, and nested `children`. Child protocol failures expose a structured `protocolError`; `protocol_output_limit` means a child emitted a JSONL line above the 16 MiB live-parser cap. Prefer these artifacts and `status` views over scraping terminal output.
+Runtime config can change orchestration behavior. `intercomBridge.resultDelivery: false` disables only external acknowledged grouped-result delivery when native parent notifications own completion; supervisor asks/progress stay active, and enabled transport failures are still reported. `asyncByDefault` and `forceTopLevelAsync` affect whether launches detach; `waitTool` can make direct `subagent_wait()` calls return immediately while headless auto-drain remains active, and its effective value is propagated to child runtimes; `globalConcurrencyLimit` bounds concurrent fanout, while a positive `maxSubagentSpawnsPerSession` optionally caps cumulative launches (`0` or unset is unlimited). Status and doctor report the budget; static work preflights declared capacity; only the settled root interactive parent can use `grant-spawn-budget` after native confirmation, with total grants bounded by the original cap. Compaction does not reset usage or grants; `singleRunOutputBaseDir` and `worktreeBaseDir` route outputs and worktrees; `completionBatch` groups async notifications. `artifactDir` is `session` (default), `project`, or `temp` and chooses where subagent artifacts are stored. Set `asyncWidget: false` to hide the above-editor background-run widget when a companion footer or dashboard owns that space (fleet inspector remains available). Per-run `artifacts: false` disables artifact capture for that launch. Async status and result artifacts include `lifecycleArtifactVersion` and fields such as `workflowGraph`, `steps`, `results`, `totalTokens`, `totalCost`, `turnCount`, `toolCount`, and nested `children`. Child protocol failures expose a structured `protocolError`; `protocol_output_limit` means a child emitted a JSONL line above the 16 MiB live-parser cap. Prefer these artifacts and `status` views over scraping terminal output.
+
+### Keep report artifacts out of the repository root
+
+Treat lane reports, review notes, council pass reports, and gate logs as scratch unless the user explicitly asks to keep them. Prefer `output: false` and the aggregate workflow result for short reports. When a later step needs a file, use the runtime-managed output artifact by setting a stable child key plus a relative `output` path such as `plans/deploy.md`; relative child outputs are saved under the run artifact directory, not the project root. Do not put `reports/...`, `*-report.json`, or similar repo-root paths in child task text.
+
+For durable evidence, copy only the final summary to session memory, a PR body/comment, a mission artifact, or a user-approved docs path outside the repo. After the PR, issue, or gate reaches a terminal state, delete or move scratch reports from the active worktree before reporting completion. Keep a project `.gitignore` entry for ad-hoc report patterns only as a safety net; it is not the cleanup mechanism.
 
 ## Best Practices
 
@@ -29,11 +37,12 @@ Launch every subagent asynchronously by default. Use `async: true` for scouts, r
 
 ### Use subagent_wait() to block until async runs finish
 
-In an interactive chat, do not call `subagent_wait()` merely to wait after launching background work; return control to the user and Selesai will wake the session on completion. Override that default when the current request is run-to-completion — for example, the user asked you to stay with the task and report results back this turn or a skill must finish in one turn. In a headless run, Selesai auto-drains exact current-session work at `agent_end`; call `subagent_wait()` when this turn must receive results before it ends. In either case, `subagent_wait()` blocks the current turn until the next run completes or needs attention, keeps the turn alive for normal notification delivery, then returns.
+In an interactive chat, do not call `subagent_wait()` merely to wait after launching background work; return control to the user and Pi will wake the session on completion. Override that default when the current request is run-to-completion — for example, the user asked you to stay with the task and report results back this turn or a skill must finish in one turn. In a headless run, Pi auto-drains exact current-session work at `agent_end`; call `subagent_wait()` when this turn must receive results before it ends. In either case, `subagent_wait()` blocks the current turn until the next run completes or needs attention, keeps the turn alive for normal notification delivery, then returns.
 
 - `subagent_wait()` — return when the next initially active async run or registered provider item finishes, or a subagent needs attention.
 - `subagent_wait({ all: true })` — block until every async run and provider item active at call time finishes, or a subagent needs attention.
 - `subagent_wait({ id: "..." })` — block on one async or remembered detached foreground run (id or prefix). Provider items are not selected through this parameter.
+- `subagent_wait({ stopOnAttention: false })` — for blocking waits only, keep waiting through idle or long-thinking attention; supervisor/contact requests still stop the wait.
 - `subagent_wait({ timeoutMs })` — cap the block; active work keeps running if it elapses.
 
 Providers are discovered through the `pi-subagents/background-work` registry and must return stable item IDs with exact owning session IDs. Child agents receive no provider automatically: keep `subagent_wait` in the child `tools` allowlist and load provider extensions through `extensions` or `subagentOnlyExtensions`.
@@ -59,10 +68,23 @@ user explicitly requests forked context.
 Give subagents specific tasks rather than vague mandates.
 `Review auth.ts for null-check gaps` works better than `Review everything`.
 
+Before fanout, assign each child a lightweight task profile in the parent prompt:
+work kind, required input, expected output, acceptance check, and context mode.
+Keep the profile prose-only; do not invent runtime fields. Use coarse kinds such
+as `code-write`, `code-read`, `transform`, `summarize`, and `search` only to
+shape the task and choose an existing agent/model setting. If a child task is not
+standalone enough for fresh context, add the missing facts to the prompt, switch
+to forked context, or ask the user. Do not launch vague tasks and rely on
+supervisor round-trips to recover missing context.
+
 ### Escalate decisions upward
 
 If a subagent encounters an unapproved product, architecture, scope, merge, release, credential, or authority choice, it should use `contact_supervisor` and wait for the reply instead of deciding alone. Generic `intercom` is external or provider-supplied only. Use it only when external bridge instructions provide an explicit safe target. External checks, receipts, and review bots provide evidence only; they do not grant authority.
 
+### Use a short oracle consultation for material advice
+
+When a user asks to ask, consult, discuss with, or come to agreement with `oracle` about a plan, design, or architecture decision, do not treat the first advisory report as final when it raises a material challenge or tradeoff. Read it, resume the same oracle session once with a targeted question, then make the parent decision. An explicit one-shot request, a trivial question, or a fully settled first answer does not need a follow-up.
+
 ### Intervene only on clear control signals
 
 Use subagent control proactively when a delegated run emits `needs_attention`, or when a human asks you to regain control. Do not interrupt just because a child has briefly produced no output. Silence can be normal during long tool calls, test runs, or model reasoning.
@@ -77,8 +99,8 @@ Use `/name` so intercom targeting stays stable.
 
 ```js
 subagent({ workflowScript: `
-  const context = await runs.run("recon", { agent: "scout", task: "Inspect the codebase and identify the implementation seam" });
-  return (await runs.run("implement", { agent: "worker", task: "Implement from: " + context.output })).output;
+  const context = await runs.run("recon", { agent: "scout", task: "Start from the named source roots, paths, and symbols. Identify the implementation seam before broad search." });
+  return (await runs.run("implement", { agent: "worker", task: "Read the scout output, plan paths, and named files/seams first. Implement from: " + context.output })).output;
 ` })
 ```