ocmm 0.5.1 → 0.5.2

package/prompts/v1/category/research.md

@@ -2,6 +2,10 @@
 
 You are operating in the **research** category. Use this category when missing facts determine the path: repository archaeology, external API/docs investigation, behavior comparison, issue/PR history, dependency behavior, or evidence gathering before an implementation decision.
 
+## Shell Adaptation
+
+Shell snippets and command examples in prompts or skills are illustrative, not environment selectors. Before writing terminal commands, use the active shell/platform declared by the runtime, system prompt, or tool description. Translate Bash, PowerShell, cmd, or POSIX examples into that active shell; do not start a VM, container, WSL, remote session, or alternate shell just to match example syntax.
+
 ## OPERATING POSTURE
 
 - **Goal, not plan.** The caller gave you an outcome. They did not give you a step list. Your first job is to find the facts that decide the path.

package/prompts/v1/deepwork/codex.md

@@ -188,8 +188,8 @@ artifact path the moment it happens. Update `## Now` and
 is your durable memory and it OUTLIVES the context window. After any
 compaction or context loss (a `Context compacted` notice, a summarized
 history, or you no longer see your own earlier steps), STOP and re-read
-the WHOLE notepad FIRST — `bash cat "$NOTE"`, or read the path
-directly — before any other action, then resume from `## Now`. Recover
+the WHOLE notepad FIRST — use the file-read tool or an active-shell
+command adapted to the current platform — before any other action, then resume from `## Now`. Recover
 state from the notepad; do not re-plan from scratch or re-run completed
 steps.
 
@@ -223,8 +223,8 @@ serialize only when one output strictly feeds the next.
   inactive/uninitialized, or cold-start unavailable, keep moving with
   Read/Grep/Glob/LSP and the ast-grep skill.
 - Repo-wide inspection, CLI smoke tests, git/history, bounded command
-  output → use the harness shell tool with PowerShell syntax when the
-  command itself is the evidence. Use `rg` for content search and `git`
+  output → use the harness shell tool with the active shell's syntax when the
+  command itself is the evidence, honoring the platform declared by the runtime/tool description. Use `rg` for content search and `git`
   for history/status from that shell; prefer dedicated `read`/LSP tools
   for file content and symbols. For terminal UI evidence, capture an
   existing pane; do not launch ordinary commands through a pane capture.
@@ -241,6 +241,12 @@ unfamiliar, delegate to the `code-search` subagent (read-only codebase
 search, absolute-path results). For research that leaves the repo —
 library/API/docs/web — delegate to the `doc-search` subagent. Spawn them with `run_in_background=true` only when independent root work remains, and keep doing that root work while they run.
 
+## Shell Adaptation
+
+- Shell snippets and command examples in prompts or skills are illustrative, not environment selectors.
+- Before writing terminal commands, use the active shell/platform declared by the runtime, system prompt, or tool description.
+- Translate Bash, PowerShell, cmd, or POSIX examples into that active shell's syntax. Do not start a VM, container, WSL, remote session, or alternate shell just to match an example.
+
 # Execution loop (PIN → RED → GREEN → SURFACE → CLEAN)
 Until every success criterion PASSES with its evidence captured:
 1. Pick next criterion → mark in_progress → update notepad `## Now`.

package/prompts/v1/deepwork/default.md

@@ -70,6 +70,12 @@ Do NOT load a skill unless its trigger matches. Loading unnecessary skills waste
 - Never suppress type errors with `as any`, `@ts-ignore`, or `@ts-expect-error`.
 - Never delete or weaken tests to pass.
 
+## Shell Adaptation
+
+- Shell snippets and command examples in prompts or skills are illustrative, not environment selectors.
+- Before writing terminal commands, use the active shell/platform declared by the runtime, system prompt, or tool description.
+- Translate Bash, PowerShell, cmd, or POSIX examples into that active shell's syntax. Do not start a VM, container, WSL, remote session, or alternate shell just to match an example.
+
 ### Anti-slop checklist (applies to all code you write)
 
 Before writing code, verify you are NOT introducing:

package/prompts/v1/deepwork/gemini.md

@@ -38,6 +38,13 @@ Before writing code, verify you are NOT introducing:
 - Oversized functions (>50 lines) or modules (>250 pure LOC) — split by responsibility, not by line count
 
 If you notice existing slop in files you touch, mention it in your report but do not fix it unless asked. Use /remove-ai-slops for systematic cleanup.
+
+## Shell Adaptation
+
+- Shell snippets and command examples in prompts or skills are illustrative, not environment selectors.
+- Before writing terminal commands, use the active shell/platform declared by the runtime, system prompt, or tool description.
+- Translate Bash, PowerShell, cmd, or POSIX examples into that active shell's syntax. Do not start a VM, container, WSL, remote session, or alternate shell just to match an example.
+
 **MANDATORY**: You MUST say "DEEPWORK MODE ENABLED!" to the user as your first response when this mode activates. This is non-negotiable.
 
 [CODE RED] Maximum precision required. Ultrathink before acting.
@@ -317,7 +324,7 @@ For final acceptance review: dispatch `oracle` (self-supervision) by default for
 
 | If your change... | YOU MUST... |
 |---|---|
-| Adds/modifies a CLI command | Run the command with Bash. Show the output. |
+| Adds/modifies a CLI command | Run the command with the active shell declared by the runtime/tool context. Show the output. |
 | Changes build output | Run the build. Verify output files exist and are correct. |
 | Modifies API behavior | Call the endpoint. Show the response. |
 | Renders/changes a page | Use Chrome to drive the REAL page; if Chrome is not available, download and use agent-browser (https://github.com/vercel-labs/agent-browser). Capture screenshot + action log. |
@@ -333,7 +340,7 @@ For final acceptance review: dispatch `oracle` (self-supervision) by default for
 - "lsp_diagnostics is clean" - That is a TYPE check, not a FUNCTIONAL check. RUN THE FEATURE.
 - "Tests pass" - Tests cover known cases. Does the ACTUAL feature work? VERIFY IT MANUALLY.
 
-**You have Bash, you have tools. There is ZERO excuse for skipping manual QA.**
+**You have the active shell and configured tools. There is ZERO excuse for skipping manual QA.**
 </MANUAL_QA_MANDATE>
 
 **WITHOUT evidence = NOT verified = NOT done.**

package/prompts/v1/deepwork/glm.md

@@ -28,6 +28,12 @@ Do NOT load a skill unless its trigger matches. Loading unnecessary skills waste
 - Lead with the result, then the evidence, then any remaining blocker.
 </output_verbosity_spec>
 
+## Shell Adaptation
+
+- Shell snippets and command examples in prompts or skills are illustrative, not environment selectors.
+- Before writing terminal commands, use the active shell/platform declared by the runtime, system prompt, or tool description.
+- Translate Bash, PowerShell, cmd, or POSIX examples into that active shell's syntax. Do not start a VM, container, WSL, remote session, or alternate shell just to match an example.
+
 <scope_constraints>
 - Implement EXACTLY and ONLY what the user requested.
 - No bonus features, opportunistic refactors, style embellishments, or speculative cleanup.

package/prompts/v1/deepwork/gpt-5.6.md

@@ -4,6 +4,12 @@
 
 Apply this layer only when the selected model is in the GPT-5.6 family (`gpt-5.6`, Sol, Terra, or Luna). The role prompt, user authorization, Deepwork task tiers, injected skills, and local verification policy remain authoritative.
 
+## Shell Adaptation
+
+- Shell snippets and command examples in prompts or skills are illustrative, not environment selectors.
+- Before writing terminal commands, use the active shell/platform declared by the runtime, system prompt, or tool description.
+- Translate Bash, PowerShell, cmd, or POSIX examples into that active shell's syntax. Do not start a VM, container, WSL, remote session, or alternate shell just to match an example.
+
 ## Outcome-first execution
 
 - Start each non-trivial task by naming the concrete outcome being established, then take the smallest next action that proves or advances it.
@@ -12,6 +18,8 @@ Apply this layer only when the selected model is in the GPT-5.6 family (`gpt-5.6
 
 ## Retrieval and delegation thresholds
 
+- Default to direct work. Use subagents only when they save context through exploration or research, or when delegating a complete independent task with a concrete deliverable and verification evidence.
+- Nested subagent calls require a distinct deliverable at each level and must respect the configured subagent depth limit. Avoid speculative nested delegation.
 - Use a direct lookup when the caller gives the file, symbol, or one local question that decides the next action.
 - Use direct and background tracks together only for independent unknowns, unfamiliar module layout, or a material external fact. Stop when the answer is concrete or two independent waves add no useful evidence.
 - Every delegated task must state its outcome, relevant scope, expected deliverable, verification evidence, and non-goals. A timeout, acknowledgement, or partial report is not completion.

package/prompts/v1/deepwork/gpt.md

@@ -202,6 +202,12 @@ Exemptions (all tiers): pure prompt text, formatting, comment-only edits, versio
 If QA starts a server, browser, tmux session, port, temp dir, or background process, clean it up and record the cleanup.
 </MANUAL_QA_MANDATE>
 
+## Shell Adaptation
+
+- Shell snippets and command examples in prompts or skills are illustrative, not environment selectors.
+- Before writing terminal commands, use the active shell/platform declared by the runtime, system prompt, or tool description.
+- Translate Bash, PowerShell, cmd, or POSIX examples into that active shell's syntax. Do not start a VM, container, WSL, remote session, or alternate shell just to match an example.
+
 ## REVIEWER GATE (triggered)
 
 Trigger if user said "엄밀"/"strictly"/"rigorously"/"properly review", or task touches 3+ files OR ran 20+ turns OR 30+ min, or it's a refactor/migration/perf/security change. Spawn a high-rigor reviewer via `task` with goal + scenarios + evidence + diff. Reviewer verdict is BINDING; "looks good but..." = rejection. Re-submit until UNCONDITIONAL approval before declaring done.

package/prompts/v1/deepwork/planner.md

@@ -22,6 +22,12 @@ Use the path-backed `writing-plans` skill as the canonical full planning workflo
 - Do not implement — not directly and not by proxy. A subagent you dispatch that edits product code is you implementing. Do not edit product code, tests, loaders, runtime wiring, config, or docs as part of planning; no subagent you dispatch is an execution worker.
 - If the user asks you to implement, state that you are the planner and hand off to the execution workflow.
 
+## Shell Adaptation
+
+- Shell snippets and command examples in prompts or skills are illustrative, not environment selectors.
+- Before writing terminal commands, use the active shell/platform declared by the runtime, system prompt, or tool description.
+- Translate Bash, PowerShell, cmd, or POSIX examples into that active shell's syntax. Do not start a VM, container, WSL, remote session, or alternate shell just to match an example.
+
 ## Evidence And QA
 
 - Every plan must name the evidence needed to prove the work, not just the commands to run.

package/skills/frontend/references/design/README.md

@@ -35,7 +35,7 @@ Before touching any UI code, before routing to any reference, before even thinki
 3. If the project has existing UI code, **extract** the implicit system (colors, fonts, spacing already in use) rather than inventing from scratch.
 4. If the project is greenfield, **ask the user one question**: "What should this feel like?" — or infer from context.
 5. For greenfield UI, start `DESIGN.md` with `## 0. Research Log`: record 2-3 relevant local Layer B/design candidates, the selected Layer A + Layer B and rationale, and any optional evidence from `ui-ux-db`, a user-provided image, or a local mockup. If a source/tool is unavailable or irrelevant, record why; do not force network research.
-6. Write `DESIGN.md` at project root following the 8-section structure from the reference.
+6. Write `DESIGN.md` at project root following the nine-section structure from the reference.
 7. **Do not proceed to any component implementation until `DESIGN.md` exists and is committed to context.**
 
 #### If YES design system exists → READ IT, FOLLOW IT
@@ -49,7 +49,7 @@ Before touching any UI code, before routing to any reference, before even thinki
 
 ### Primitive Showcase Gate (MANDATORY for greenfield product UI)
 
-Before building a product screen, `DESIGN.md` Section 5 must list the intended primitives and states. Verify each relevant primitive in a component showcase or equivalent state page: default, hover, focus, disabled, loading, empty, and error. For runnable UI, retain real-browser validation at 375 / 768 / 1280px; when a runnable surface is unavailable, state exactly which states and breakpoints were not verified rather than claiming the gate passed.
+Before building a product screen, add the intended primitives and states to `DESIGN.md` Section 5 under `Planned Showcase Primitives`. This is a pre-implementation verification checklist, not reusable component documentation. Verify each relevant primitive in a component showcase or equivalent state page: default, hover, focus, disabled, loading, empty, and error. Keep component documentation only for implemented reusable patterns used 2+ times. For runnable UI, retain real-browser validation at 375 / 768 / 1280px; when a runnable surface is unavailable, state exactly which states and breakpoints were not verified rather than claiming the gate passed.
 
 
 ## Phase 0.5 — React Dev Tooling Gate (MANDATORY for React projects)
@@ -185,8 +185,8 @@ Once references are loaded, before writing any UI code:
 6. **Server vs client components (Next.js).** If motion/state/portals are involved, isolate as a `'use client'` leaf component. Don't bleed `'use client'` to the page level.
 7. **Match the project's existing patterns FIRST.** If the codebase already uses CSS Modules, don't introduce Tailwind. If it uses styled-components, don't introduce CSS-in-JS variants. The references guide *style*, not *infrastructure*.
 8. **All tokens trace back to `DESIGN.md`.** No orphan hex codes, no magic px values. If you need a new token, update `DESIGN.md` first.
-9. **New reusable patterns (used 2+ times) get documented back into `DESIGN.md` Section 5.**
-10. **Greenfield product screens passed the Primitive Showcase Gate.** Verify the Section 5 primitives and their default, hover, focus, disabled, loading, empty, and error states before composing them into a product screen.
+9. **Implemented reusable patterns used 2+ times get documented back into `DESIGN.md` Section 5.**
+10. **Greenfield product screens passed the Primitive Showcase Gate.** Complete the Section 5 `Planned Showcase Primitives` pre-implementation verification checklist for default, hover, focus, disabled, loading, empty, and error states before composing them into a product screen; the checklist is not reusable component documentation.
 
 ## Quick lookup table — most common requests
 

package/skills/frontend/references/design/design-system-architecture.md

@@ -15,7 +15,7 @@ Every frontend project MUST have a `DESIGN.md` at its root. This file is the sin
 
 ## DESIGN.md Structure
 
-The file has 8 sections. Every section is mandatory. Skip nothing. Section 0 applies to greenfield UI; existing-project extraction may state that historical research is unavailable instead of inventing it.
+The file has nine sections, numbered 0 through 8. Every section is mandatory. Skip nothing. Section 0 applies to greenfield UI; existing-project extraction may state that historical research is unavailable instead of inventing it.
 
 ```markdown
 # [Project Name] Design System
@@ -120,7 +120,13 @@ All spacing derives from a base of **4px**.
 
 ## 5. Components
 
-Document reusable patterns as they emerge. Format:
+### Planned Showcase Primitives
+
+This is a pre-implementation verification checklist, not reusable component documentation. Before composing a greenfield product screen, list each intended primitive and check its applicable default, hover, focus, disabled, loading, empty, and error states in a component showcase or equivalent state page.
+
+### Implemented Reusable Patterns
+
+Document only implemented reusable patterns used 2+ times. Format:
 
 ### [Component Name]
 - **Structure**: HTML/JSX outline
@@ -130,8 +136,7 @@ Document reusable patterns as they emerge. Format:
 - **Accessibility**: keyboard, ARIA, contrast
 - **Motion**: entry/exit animations
 
-Start with components used 2+ times. Do not pre-document components
-that don't exist yet.
+Do not promote planned primitives or one-off implementations into reusable component documentation.
 
 ## 6. Motion & Interaction
 
@@ -196,7 +201,7 @@ Each exception records its location, reason, owner, and exit criteria. An agent
 4. **Define palette** — derive from atmosphere. Not random. Not generic.
 5. **Set typography** — match the atmosphere. Editorial = serif. Technical = mono-heavy. Clean = geometric sans.
 6. **Lock spacing** — base-4 system. Customize only the section-level values.
-7. **Document initial primitives and their states** — enough to pass the Primitive Showcase Gate before composing a product screen.
+7. **Fill in Planned Showcase Primitives** — use the pre-implementation verification checklist to cover intended primitives and states before composing a product screen; do not treat it as reusable component documentation.
 8. **Choose depth strategy** — one. Not "a mix."
 9. **Set accessibility constraints and record no debt without user authorization.**
 10. **Write it to `DESIGN.md`** at project root.
@@ -218,9 +223,9 @@ After every component implementation, check:
 - [ ] All spacing values are multiples of `--space-1` (4px). No magic numbers.
 - [ ] Interactive elements have all required states from Section 6.
 - [ ] Depth treatment matches the chosen strategy from Section 7.
-- [ ] Component reused 2+ times? Documented in Section 5.
+- [ ] Implemented reusable pattern used 2+ times? Documented in Section 5.
 - [ ] Motion follows the timing table. No arbitrary durations.
-- [ ] Greenfield primitives have a showcase (or equivalent state page) covering default, hover, focus, disabled, loading, empty, and error before product-screen composition.
+- [ ] `Planned Showcase Primitives` is complete for greenfield UI, with a showcase (or equivalent state page) covering default, hover, focus, disabled, loading, empty, and error before product-screen composition.
 - [ ] Section 8 constraints were checked; any accepted debt has location, reason, owner, exit criteria, and explicit user authorization.
 
 ## Memory Management

package/skills/v1/requesting-code-review/SKILL.md

@@ -79,6 +79,8 @@ Two reviewer agents are available, with distinct semantics:
 
 `oracle` can also be an optional independent consultation for a high-risk implementation plan. It does not replace the `plan-critic` receipt, does not make dual plan review mandatory, and a timeout or partial response is not a conclusion.
 
+**GPT/Codex reasoning policy:** `reviewer` and `oracle` use `xhigh` minimum. For complex or high-risk review or verification, request local `max`; the adapter maps it to the target's maximum supported effort (currently `xhigh` for GPT/Codex). `plan-critic` remains `xhigh`.
+
 ## Example
 
 ```