@wrongstack/core 0.299.0 → 0.301.0

package/skills/auto-review/SKILL.md

@@ -7,6 +7,9 @@ description: |
   Triggers: user says "auto review", "otomatik review", "auto code review",
   "her değişiklikte review", "/auto-review".
 version: 2.0.0
+required-capabilities: [version-control.manage]
+required-tools: [git]
+optional-capabilities: [fleet.delegate, verification.run]
 ---
 
 # Auto Review — Built-in Plugin
@@ -48,6 +51,7 @@ Enable it in your config:
       "provider": "deepseek",
       "model": "deepseek-chat",
       "fallbackProfile": "reliable",
+      "modelSelection": "round-robin",
       "debounceMs": 15000,
       "maxFilesPerBatch": 15
     }
@@ -69,7 +73,8 @@ Enable it in your config:
 | `enabled` | boolean | false | Master switch |
 | `provider` | string | session provider | LLM provider for review agents |
 | `model` | string | session model | LLM model for review agents |
-| `fallbackProfile` | string | effective fallback profile | Named profile from `fallbackProfiles`; its first valid entry supplies the primary provider/model when those are omitted |
+| `fallbackProfile` | string | effective fallback profile | Named profile from `fallbackProfiles`; its first valid entry supplies the primary provider/model when those are omitted, and its entries form the reviewer selection and retry pool |
+| `modelSelection` | `round-robin` \| `random` | `round-robin` | Choose each review's starting model in profile order or randomly; remaining entries stay available as fallbacks |
 | `debounceMs` | number | 15000 | Required file-quiet period before a mid-session review starts |
 | `maxFilesPerBatch` | number | 15 | Files per review call |
 | `maxConcurrentReviews` | number | 2 | Parallel review subagent cap |

package/skills/bug-hunter/SKILL.md

@@ -11,6 +11,9 @@ description: |
   agent behind a chimera review, or as a fan-out worker auditing a chunk of
   files in parallel — those modes have extra constraints documented below.
 version: 2.0.0
+required-capabilities: [filesystem.read, code.inspect]
+required-tools: []
+optional-capabilities: [verification.run]
 ---
 
 # Bug Hunter — WrongStack
@@ -298,4 +301,4 @@ sizing and briefing rules before dispatching.
 - Summary counts match the findings listed
 - `<nextsteps>` mirrors the findings in severity order
 - In cascade mode: fixes are minimal, unfixed findings are listed with reasons,
-  and no mailbox message was sent
+  and no mailbox message was sent

package/skills/chimera/SKILL.md

@@ -12,6 +12,9 @@ description: |
   wants the fixes actually applied, that is bug-hunter or security-scanner, not
   this skill — but review first, then hand off.
 version: 2.0.0
+required-capabilities: [filesystem.read, code.inspect]
+required-tools: []
+optional-capabilities: [version-control.manage]
 ---
 
 # Chimera — Post-Session Code Guardian

package/skills/data-governance/SKILL.md

@@ -7,6 +7,9 @@ description: |
   Triggers: user says "data governance", "PII", "schema ownership", "retention policy", "data lineage", "migration safety".
 trigger: Use when designing or reviewing schema ownership, PII handling, retention, data lineage, access policy, or migration safety.
 version: 1.0.0
+required-capabilities: [filesystem.read]
+required-tools: []
+optional-capabilities: [code.inspect]
 ---
 
 # Data Governance — WrongStack

package/skills/design-system/SKILL.md

@@ -16,6 +16,9 @@ description: |
   brand", "add dark mode". Trigger even when the user never says the word
   "design" — if the output has pixels, this skill runs first.
 version: 2.0.0
+required-capabilities: [filesystem.read, filesystem.write, documentation.author]
+required-tools: [design]
+optional-capabilities: [browser.interact]
 ---
 
 # Design System Engine — WrongStack
@@ -116,7 +119,7 @@ For a genuinely specific color (brand primary, a mandated status color):
 design {action:"set", set:{ primary:"oklch(62% 0.2 25)", "dark.bg":"#111" }}
 ```
 
-Use `set` for the handful of values the brand actually dictates. Everything
+Use the `design` tool's `set` action for the handful of values the brand actually dictates. Everything
 else stays on the kit.
 
 ---
@@ -147,7 +150,7 @@ Then, without exception:
 2. **Read the generated file before writing UI.** It is the ground truth for
    which token names exist. Do not guess names from this document or from
    another project — use the ones actually in the file.
-3. Re-run `materialize` after any later `tune` or `set`, or the code and the
+3. Re-run the `design` tool with the `materialize` action after any later `tune` or `set`, or the code and the
    tokens silently diverge.
 
 ---

package/skills/docker-deploy/SKILL.md

@@ -6,6 +6,8 @@ description: |
   "image", "docker-compose", "deploy", "containerize", "registry",
   "multi-stage", "distroless".
 version: 1.0.0
+required-capabilities: [filesystem.read, filesystem.write, execution.shell]
+required-tools: []
 ---
 
 # Docker Deploy — WrongStack

package/skills/git-flow/SKILL.md

@@ -5,6 +5,8 @@ description: |
   branches, pull requests, or merge strategies in a WrongStack project session.
   Triggers: user mentions "commit", "branch", "PR", "merge", "rebase", "stash", "diff".
 version: 1.2.0
+required-capabilities: [version-control.manage]
+required-tools: [test]
 ---
 
 # Git Workflow — WrongStack

package/skills/mailbox-bridge/SKILL.md

@@ -9,6 +9,9 @@ description: |
   WrongStack-internal agents already share, so any agent with curl or
   fetch can read, send, and acknowledge messages.
 version: 1.0.0
+required-capabilities: [execution.shell]
+required-tools: []
+optional-capabilities: [web.research]
 ---
 
 # Mailbox Bridge — Expose the Shared Mailbox to External Agents

package/skills/mnemosyne/SKILL.md

@@ -5,6 +5,8 @@ description: |
   anchor verification first, then review contradictions, drift, and noise;
   file destructive outcomes as review proposals instead of deleting directly.
 version: 1.1.0
+required-capabilities: [memory.manage, memory.curate]
+required-tools: [cron_cancel, cron_schedule, mail_send, mailbox, memory_candidates, memory_delete, memory_hygiene, memory_search, memory_update, memory_verify, skill]
 ---
 
 # Mnemosyne — SAGE Memory Custodian

package/skills/multi-agent/SKILL.md

@@ -15,6 +15,9 @@ description: |
   synthesized into one report, or when deciding whether parallelism is worth it
   at all — talking someone out of fanning out is a valid use of this skill.
 version: 2.0.0
+required-capabilities: [fleet.delegate]
+required-tools: [collab_debug, delegate, glob, grep, plan, read, test]
+optional-capabilities: [coordination.mailbox, work.plan]
 ---
 
 # Multi-Agent Coordination — WrongStack
@@ -365,4 +368,4 @@ session that dies halfway — and they let you synthesize as you go.
 - Findings deduplicated, cross-target patterns called out as systemic
 - Prioritized critical → low, not left in worker-arrival order
 - A sample of worker claims spot-checked against the actual code
-- Report presents synthesis, not concatenation
+- Report presents synthesis, not concatenation

package/skills/node-modern/SKILL.md

@@ -5,6 +5,9 @@ description: |
   TypeScript code in WrongStack. Triggers: ESM imports, fetch usage, AbortSignal,
   node: protocol, Web Streams, or any async patterns.
 version: 1.1.0
+required-capabilities: [filesystem.read, filesystem.write]
+required-tools: []
+optional-capabilities: [verification.run]
 ---
 
 # Modern Node.js (>= 22) — WrongStack
@@ -150,7 +153,7 @@ while (true) {
 
 | Anti-pattern | Why bad | Fix |
 |---|---|---|
-| `require()` in new code | WrongStack uses ESM | Use `import` with `.js` extension |
+| `require()` in new code | WrongStack uses ESM | Prefer `import` with `.js` extension |
 | `__dirname` without `fileURLToPath` | ESM doesn't have `__dirname` | `path.dirname(fileURLToPath(import.meta.url))` |
 | Mixing `fs.readFile` callback with `await` | Callback API doesn't return a promise | Use `fs.promises.readFile` |
 | Swallowing `AbortError` silently | Means timeout/abort happened | Log it or handle explicitly |

package/skills/observability/SKILL.md

@@ -6,6 +6,9 @@ description: |
   "log", "trace", "metrics", "observability", "instrument", "structured logging",
   "opentelemetry", "log level", "debug", "monitoring".
 version: 1.0.0
+required-capabilities: [filesystem.read, filesystem.write]
+required-tools: []
+optional-capabilities: [code.inspect]
 ---
 
 # Observability — WrongStack

package/skills/output-standards/SKILL.md

@@ -5,6 +5,8 @@ description: |
   responses in WrongStack. Triggers: user says "next steps format", "output standard",
   "response format", "final message format", "standardize next steps".
 version: 1.0.0
+required-capabilities: []
+required-tools: []
 ---
 
 # Output Standards — WrongStack

package/skills/plugin-author/SKILL.md

@@ -8,6 +8,9 @@ description: |
   Triggers: user says "new plugin", "add a plugin", "plugin teardown", "plugin
   health", "register a tool", "PluginAPI extension".
 version: 1.0.0
+required-capabilities: [filesystem.read, filesystem.write, execution.shell]
+required-tools: [bash, cron_cancel, cron_list, cron_schedule, edit, fetch, git, git_autocommit, json, read, search, secret_scanner_test, semver_bump, semver_changelog, semver_current, todo, watch_list, watch_start, watch_stop, write]
+optional-capabilities: [verification.run]
 ---
 
 # Plugin Author — WrongStack
@@ -64,7 +67,7 @@ There are currently **21 official plugins** in the suite:
    (todo-tracker) leave the file in place — the user may return. Only
    in-memory counters and resource handles (timers, watchers) are
    cleaned up.
-5. **Tool names use `snake_case`.** Plugin-level tools registered via
+5. **Tool names follow `snake_case`.** Plugin-level tools registered via
    `api.tools.register()` must be unique across the suite. The built-in
    tools (`bash`, `write`, `read`, `edit`, `fetch`, `search`, `json`,
    `todo`, `git`, etc.) are always present; don't collide.

package/skills/prompt-engineering/SKILL.md

@@ -5,6 +5,8 @@ description: |
   tool descriptions, skill definitions, or LLM instruction text in WrongStack.
   Triggers: user mentions "prompt", "system instruction", "skill description", "tool hint", "usage hint", "system prompt".
 version: 1.1.0
+required-capabilities: [filesystem.read, filesystem.write]
+required-tools: []
 ---
 
 # Prompt Engineering — WrongStack
@@ -134,4 +136,4 @@ See `skill-creator` skill for the format. Key points:
 - `skill-creator` — for creating new skills (primary — prompt-engineering feeds into skill creation)
 - `typescript-strict` — for TypeScript-specific prompt typing
 - `react-modern` — for React component prompt conventions
-- `output-standards` — for standardized `<nextsteps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/react-modern/SKILL.md

@@ -5,6 +5,9 @@ description: |
   Triggers: user mentions "React", "component", "useState", "useEffect",
   "Server Component", "Client Component", "Suspense", "useTransition", "use hook".
 version: 1.1.0
+required-capabilities: [filesystem.read, filesystem.write]
+required-tools: []
+optional-capabilities: [verification.run]
 ---
 
 # Modern React (19+) — WrongStack
@@ -17,8 +20,8 @@ React 19+ patterns: Server Components by default, `use` hook for promises, `useT
 
 1. Default to Server Components — mark `'use client'` only for interactive code.
 2. Keep the client boundary minimal — avoid unnecessary serialization errors.
-3. Don't use `useEffect` for data fetching — use Server Components or `use(promise)`.
-4. Don't use `forwardRef` in new code — `ref` is a regular prop in React 19.
+3. Avoid `useEffect` for data fetching — prefer Server Components or `use(promise)`.
+4. Avoid `forwardRef` in new code — `ref` is a regular prop in React 19.
 5. Use named exports for components — default exports hinder refactoring.
 6. Event handlers must have explicit types: `React.MouseEvent<HTMLButtonElement>`.
 
@@ -209,4 +212,4 @@ const inputRef = useRef<HTMLInputElement>(null);
 - `typescript-strict` — for TypeScript patterns
 - `node-modern` — for React server components with Node.js
 - `bug-hunter` — for React-specific bugs (stale closures, memory leaks)
-- `output-standards` — for standardized `<nextsteps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/refactor-planner/SKILL.md

@@ -12,6 +12,8 @@ description: |
   it does not perform the refactor. Use it before touching code, and when a
   refactor already in flight has lost its ordering.
 version: 2.0.0
+required-capabilities: [filesystem.read, code.inspect, work.plan]
+required-tools: []
 ---
 
 # Refactor Planner — WrongStack

package/skills/research-web/SKILL.md

@@ -9,6 +9,9 @@ description: |
   "latest", "what's new in", "breaking changes", "find current",
   "web research", "search the web", "look up".
 version: 1.0.0
+required-capabilities: [web.research]
+required-tools: [context_manager, delegate, fetch, search]
+optional-capabilities: [runtime.admin]
 ---
 
 # Research Web — WrongStack

package/skills/sdd/SKILL.md

@@ -5,6 +5,8 @@ description: |
   in WrongStack. Triggers: user says "/sdd", "spec", "specification", "task graph",
   "SDD", "acceptance criteria", or starts a new feature.
 version: 2.1.0
+required-capabilities: [work.plan, filesystem.write]
+required-tools: []
 ---
 
 # Spec-Driven Development — WrongStack
@@ -132,4 +134,4 @@ Stage shown in real-time. Pause stops after current iteration completes.
 - `refactor-planner` — when the spec reveals a multi-file refactor
 - `bug-hunter` — when a bugfix spec needs a root cause analysis section
 - `multi-agent` — for executing parallel task groups
-- `output-standards` — for standardized `<nextsteps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/security-scanner/SKILL.md

@@ -5,6 +5,9 @@ description: |
   in WrongStack. Triggers: user says "security", "vulnerability", "CVE", "secret",
   "injection", "XSS", "SQL injection", "audit security", "supply chain".
 version: 1.2.0
+required-capabilities: [filesystem.read, code.inspect]
+required-tools: []
+optional-capabilities: [dependencies.manage]
 ---
 
 # Security Scanner — WrongStack

package/skills/skill-creator/SKILL.md

@@ -4,6 +4,8 @@ description: |
   Use this skill when the user wants to create a new AI skill in WrongStack.
   Triggers: user says "create a skill", "new skill", "add a skill", "skill definition".
 version: 1.2.0
+required-capabilities: [filesystem.write, runtime.admin]
+required-tools: [bash, skill]
 ---
 
 # Skill Creator — WrongStack

package/skills/tech-stack/SKILL.md

@@ -5,6 +5,9 @@ description: |
   or evaluating third-party libraries in WrongStack. Triggers: user says "dependency",
   "package version", "outdated", "npm audit", "deprecated package", "tech stack".
 version: 1.2.0
+required-capabilities: [dependencies.manage]
+required-tools: []
+optional-capabilities: [web.research]
 ---
 
 # Tech Stack Validator — WrongStack (Language-Agnostic)

package/skills/testing/SKILL.md

@@ -5,6 +5,9 @@ description: |
   Triggers: user says "test", "unit test", "integration test", "e2e", "mock",
   "vitest", "coverage", "assert", "expect", "test strategy", "write tests".
 version: 1.0.0
+required-capabilities: [filesystem.read, verification.run]
+required-tools: []
+optional-capabilities: [execution.shell]
 ---
 
 # Testing — WrongStack
@@ -157,7 +160,7 @@ coverageThreshold: {
 
 ## WrongStack-specific test notes
 
-- **Subpath exports**: Some packages use `exports` field in `package.json` — tests must use the public entry point, not `dist/`.
+- **Subpath exports**: Some packages define an `exports` field in `package.json` — tests must use the public entry point, not `dist/`.
 - **AbortSignal**: Any test involving timeouts must use `AbortSignal.timeout()` not `setTimeout`.
 - **pnpm workspaces**: Run `pnpm test` in the package root, or `pnpm -r test` for all packages.
 - **Vitest config**: Each package has its own `vitest.config.ts`.

package/skills/typescript-strict/SKILL.md

@@ -5,6 +5,9 @@ description: |
   in WrongStack. Triggers: user mentions "TypeScript", "strict", "type error",
   "type safety", "narrowing", "branded type", "discriminated union", "noUncheckedIndexedAccess".
 version: 1.1.0
+required-capabilities: [filesystem.read, filesystem.write]
+required-tools: []
+optional-capabilities: [verification.run]
 ---
 
 # TypeScript Strict Mode — WrongStack
@@ -237,4 +240,4 @@ console.log(name!.toUpperCase());
 - `node-modern` — for TypeScript + ESM patterns
 - `react-modern` — for React + TypeScript patterns
 - `bug-hunter` — for type-related bugs like unsafe casts
-- `output-standards` — for standardized `<nextsteps>` formatting
+- `output-standards` — for standardized `<nextsteps>` formatting

package/skills/wrongstack-kanban/SKILL.md

@@ -10,6 +10,8 @@ triggers:
   - user says "kanban", "board", "task dispatch", "kanban queue"
   - working with the kanban tool or kanban_queue
   - managing project work through boards
+required-capabilities: [work.plan]
+required-tools: [kanban, kanban_queue]
 ---
 
 # WrongStack Kanban — Deterministic Enforcement Skill
@@ -67,12 +69,13 @@ The lifecycle guard enforces these mechanically. Do not attempt to bypass them.
    order, and creation time — not randomly. Do not attempt to influence dispatch
    order by shuffling tasks or boards.
 
-2. **Claim before working.** Call `kanban_queue` or `claim_task` before starting
+2. **Claim before working.** Call `kanban_queue`, or call `kanban` with the
+   `claim_task` action, before starting
    work. Working on an unclaimed card means another agent may also be working on
    it.
 
-3. **Heartbeat or lose the lease.** If you hold a lease, you must call
-   `heartbeat_assignment` before it expires. Expired leases are recovered by the
+3. **Heartbeat or lose the lease.** If you hold a lease, you must call `kanban`
+   with the `heartbeat_assignment` action before it expires. Expired leases are recovered by the
    system and the task is reassigned.
 
 4. **Fence your writes.** Include `expectedLeaseId` in every `mark_assignment`

package/skills/wrongstack-mailbox/SKILL.md

@@ -9,6 +9,9 @@ description: |
   fleet", "tell the wrongstack agents", "is anyone online in
   wrongstack", or "register me with wrongstack".
 version: 1.0.0
+required-capabilities: []
+required-tools: [mailbox]
+optional-capabilities: [mcp.dynamic, web.research]
 ---
 
 # WrongStack Mailbox Client
@@ -658,7 +661,7 @@ await mb('/mailbox/send', {
   credential. If you must print the URL, redact the token (`[REDACTED]`).
 - **Don't reply to a broadcast with another broadcast.** Replies should
   target the original sender via `to: <their-id>`, with `replyTo` set.
-- **Don't use `control` messages.** They go through a different path in
+- **Avoid `control` messages.** They go through a different path in
   the WrongStack agent loop and will likely be dropped on the floor by
   the recipient.
 

package/skills/wrongstack-mailbox-mcp/SKILL.md

@@ -1,6 +1,8 @@
 ---
 name: wrongstack-mailbox-mcp
 description: Coordinate with WrongStack agents through the project-scoped Mailbox MCP server. Use when an external coding agent needs to inspect unread or incomplete messages, query conversation history, discover online agents, send direct/reply/broadcast/steer messages, acknowledge outcomes, maintain its presence, soft-delete or restore messages, watch for changes, or perform explicitly authorized Mailbox administration without reading Mailbox files or SQLite directly.
+required-capabilities: [mcp.dynamic]
+required-tools: [mcp_use]
 ---
 
 # WrongStack Mailbox MCP
@@ -34,11 +36,11 @@ heartbeat identity to `--actor`; tool arguments cannot impersonate another actor
 
 ## Coordinate
 
-1. Call `mailbox_manage` with `register_self`. Include a stable name and role when known.
-2. Call `mailbox_read` with `unread`, then `query`. Prefer `unreadBy` plus `incompleteOnly` when
+1. Call `mcp_use` for the remote `mailbox_manage` operation with `register_self`. Include a stable name and role when known.
+2. Call `mcp_use` for the remote `mailbox_read` operation with `unread`, then `query`. Prefer `unreadBy` plus `incompleteOnly` when
    looking for actionable work.
-3. Use `mailbox_read` with `online_agents` before routing a time-sensitive direct message.
-4. Use `mailbox_manage` with `send`. Set an explicit recipient and message type:
+3. Call `mcp_use` for remote `mailbox_read` with `online_agents` before routing a time-sensitive direct message.
+4. Call `mcp_use` for remote `mailbox_manage` with `send`. Set an explicit recipient and message type:
    - `ask` for a blocking question;
    - `assign` for delegated work;
    - `steer` for changed direction;
@@ -46,17 +48,17 @@ heartbeat identity to `--actor`; tool arguments cannot impersonate another actor
    - `result` for a completed outcome;
    - `broadcast` only when every relevant agent should receive it.
 5. Set `replyTo` when continuing a thread. Do not create an unrelated message that loses context.
-6. Use `ack` or `ack_many` after reading or completing messages. Record a truthful outcome when
+6. Call `mcp_use` for the remote `ack` or `ack_many` operation after reading or completing messages. Record a truthful outcome when
    marking work completed.
 7. Send `heartbeat_self` during long work and `deregister_self` on a clean shutdown.
 
-Runtime-only `control` messages are deliberately unavailable. Use `steer` for normal external
+Runtime-only `control` messages are deliberately unavailable. Call `mcp_use` for the remote `steer` operation for normal external
 direction; never bypass the restriction through another channel.
 
 ## Observe changes
 
-Call `mailbox_watch` with an optional event type and timeout no greater than 25 seconds. Treat the
-result as a wake-up hint. After every event or timeout, reconcile with `mailbox_read`; watch events
+Call `mcp_use` for remote `mailbox_watch` with an optional event type and timeout no greater than 25 seconds. Treat the
+result as a wake-up hint. After every event or timeout, reconcile through remote `mailbox_read`; watch events
 contain identifiers and metadata, not the authoritative message snapshot.
 
 ## Manage and administer