codeforge-dev 1.13.0 → 1.14.2

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/docker/SKILL.md

@@ -1,14 +1,14 @@
 ---
 name: docker
 description: >-
-  This skill should be used when the user asks to "write a Dockerfile",
-  "set up Docker Compose", "create a multi-stage Docker build",
-  "add health checks to Docker Compose", "use Docker Compose watch for development",
-  "configure Docker networking", "optimize Docker image size",
-  "add secrets to Docker Compose", or discusses Dockerfile best practices,
-  Compose service orchestration, container networking, volume management,
-  build caching, resource limits, or development workflows with containers.
-version: 0.1.0
+  Guides Dockerfile authoring and Docker Compose orchestration with multi-stage
+  builds, health checks, and dev watch mode. USE WHEN the user asks to "write
+  a Dockerfile", "set up Docker Compose", "create a multi-stage build", "add
+  health checks", "use Docker Compose watch", "optimize Docker image size",
+  or works with compose.yaml, docker compose, BuildKit, Compose profiles.
+  DO NOT USE for programmatic container management from Python — use
+  docker-py instead.
+version: 0.2.0
 ---
 
 # Docker & Docker Compose

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/docker-py/SKILL.md

@@ -1,13 +1,15 @@
 ---
 name: docker-py
 description: >-
-  This skill should be used when the user asks to "manage Docker containers from Python",
-  "create containers programmatically", "stream Docker container logs",
-  "execute commands in a running container", "manage Docker volumes from code",
-  "build images with the Docker SDK", "use docker-py for container lifecycle",
-  "monitor container health from Python", or discusses docker-py,
-  aiodocker, programmatic container management, or Docker Engine API.
-version: 0.1.0
+  Provides patterns for programmatic Docker container management using the
+  Docker SDK for Python and aiodocker. USE WHEN the user asks to "manage Docker
+  containers from Python", "create containers programmatically", "stream
+  container logs", "execute commands in a running container", "build images
+  with docker-py", "monitor container health from Python", or works with
+  docker-py, aiodocker, DockerClient, Docker Engine API, container lifecycle.
+  DO NOT USE for writing Dockerfiles or Docker Compose files — use the docker
+  skill instead.
+version: 0.2.0
 ---
 
 # Docker SDK for Python

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/documentation-patterns/SKILL.md

@@ -1,12 +1,13 @@
 ---
 name: documentation-patterns
 description: >-
-  This skill should be used when the user asks to "write a README",
-  "write documentation", "add docstrings", "add JSDoc", "document the API",
-  "create architecture docs", "documentation template", "update the docs",
-  or discusses docstring formats, README structure, API documentation,
-  inline comments, or technical writing patterns.
-version: 0.1.0
+  Guides documentation authoring including README structure, docstring formats,
+  API references, and architecture docs. USE WHEN the user asks to "write a
+  README", "add docstrings", "add JSDoc", "document the API", "create
+  architecture docs", "write documentation", "update the docs", or works with
+  Google-style docstrings, Sphinx, rustdoc, TSDoc, OpenAPI annotations.
+  DO NOT USE for writing code, fixing bugs, or generating changelogs.
+version: 0.2.0
 ---
 
 # Documentation Patterns

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/fastapi/SKILL.md

@@ -1,14 +1,15 @@
 ---
 name: fastapi
 description: >-
-  This skill should be used when the user asks to "build a FastAPI app",
-  "create a REST API with FastAPI", "add SSE streaming to FastAPI",
-  "use dependency injection in FastAPI", "define Pydantic models for an API",
-  "stream LLM responses with FastAPI", "add middleware to FastAPI",
-  "handle background tasks in FastAPI", or discusses FastAPI routing,
-  Pydantic v2 models, dependency injection, server-sent events,
-  or ASGI middleware.
-version: 0.1.0
+  Teaches modern FastAPI development including REST APIs, Pydantic v2 models,
+  SSE streaming, and ASGI middleware patterns. USE WHEN the user asks to "build
+  a FastAPI app", "create a REST API with FastAPI", "add SSE streaming", "use
+  dependency injection in FastAPI", "define Pydantic models", "stream LLM
+  responses", "add middleware to FastAPI", or works with FastAPI routing,
+  Pydantic v2, sse-starlette, EventSourceResponse, APIRouter, BackgroundTasks.
+  DO NOT USE for general Python web frameworks like Flask or Django, or for
+  frontend development.
+version: 0.2.0
 ---
 
 # FastAPI Development

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/git-forensics/SKILL.md

@@ -1,14 +1,16 @@
 ---
 name: git-forensics
 description: >-
-  This skill should be used when the user asks to "find who changed this line",
-  "search git history for a deleted function", "bisect a regression",
-  "recover a lost commit", "investigate when a bug was introduced",
-  "trace the history of a file", "search commit messages",
-  "find when code was removed", "check git blame", "use git reflog",
-  or discusses git archaeology, git bisect, git log search, pickaxe,
-  blame analysis, reflog recovery, or commit history investigation.
-version: 0.1.0
+  Provides git history investigation techniques including blame analysis,
+  bisect workflows, pickaxe search, and reflog recovery for tracing code
+  changes and recovering lost work. USE WHEN the user asks to "find who
+  changed this line", "bisect a regression", "recover a lost commit",
+  "search git history", "find when code was removed", "check git blame",
+  "use git reflog", or "trace the history of a file", or works with git
+  log -S, git bisect run, or .git-blame-ignore-revs. DO NOT USE for
+  routine git operations like committing, branching, or merging.
+version: 0.2.0
+allowed-tools: Bash, Read, Grep
 ---
 
 # Git Forensics
@@ -103,7 +105,7 @@ Track a file across renames. Without `--follow`, history stops at the rename:
 # Follow a file through renames
 git log --follow --oneline -- path/to/current_name.py
 
-# Blame through renames
+# Show patch history through renames
 git log --follow -p -- path/to/file.py
 ```
 

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/migration-patterns/SKILL.md

@@ -1,12 +1,13 @@
 ---
 name: migration-patterns
 description: >-
-  This skill should be used when the user asks to "migrate from X to Y",
-  "upgrade to version N", "bump Python version", "upgrade pydantic",
-  "migrate express to fastify", "framework migration", "version upgrade",
-  "modernize the codebase", or discusses code migration, framework upgrades,
-  API version bumps, or dependency migration strategies.
-version: 0.1.0
+  Guides incremental, rollback-safe framework upgrades and dependency
+  migrations with step-by-step verification. USE WHEN the user asks to
+  "migrate from X to Y", "upgrade to version N", "bump Python version",
+  "upgrade pydantic", "migrate express to fastify", "modernize the codebase",
+  or works with Pydantic v1-to-v2, Django upgrades, CommonJS to ESM.
+  DO NOT USE for routine dependency updates without API changes.
+version: 0.2.0
 ---
 
 # Migration Patterns

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/performance-profiling/SKILL.md

@@ -1,14 +1,16 @@
 ---
 name: performance-profiling
 description: >-
-  This skill should be used when the user asks to "profile this code",
-  "find the bottleneck", "optimize performance", "measure execution time",
-  "check memory usage", "create a flamegraph", "benchmark this function",
-  "find memory leaks", "reduce latency", "run a performance test",
-  or discusses profiling tools, flamegraphs, benchmarking methodology,
-  cProfile, py-spy, scalene, Chrome DevTools performance,
-  memory profiling, or hot path analysis.
-version: 0.1.0
+  Guides measure-first performance investigation using CPU profilers, memory
+  analyzers, flamegraphs, and reproducible benchmarking across Python and
+  Node.js. USE WHEN the user asks to "profile this code", "find the
+  bottleneck", "create a flamegraph", "benchmark this function", "find
+  memory leaks", "check memory usage", "reduce latency", or "measure
+  execution time", or works with cProfile, py-spy, scalene, clinic.js,
+  Chrome DevTools, hyperfine, or pytest-benchmark. DO NOT USE for security
+  auditing, dependency management, or code refactoring.
+version: 0.2.0
+allowed-tools: Bash, Read, Glob, Grep
 ---
 
 # Performance Profiling

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/pydantic-ai/SKILL.md

@@ -1,13 +1,14 @@
 ---
 name: pydantic-ai
 description: >-
-  This skill should be used when the user asks to "build a PydanticAI agent",
-  "create an AI agent with PydanticAI", "add tools to a PydanticAI agent",
-  "stream responses with PydanticAI", "test a PydanticAI agent",
-  "connect PydanticAI to a Svelte frontend", "use RunContext for dependency injection",
-  "configure model fallbacks in PydanticAI", or discusses PydanticAI agents,
-  tool decorators, structured output, agent testing, or VercelAIAdapter.
-version: 0.1.0
+  Teaches PydanticAI agent development with tool decorators, RunContext
+  dependency injection, streaming, and VercelAIAdapter. USE WHEN the user
+  asks to "build a PydanticAI agent", "add tools to an agent", "stream
+  responses with PydanticAI", "test a PydanticAI agent", "connect PydanticAI
+  to Svelte", "configure model fallbacks", or works with pydantic-ai, Agent,
+  RunContext, TestModel, FallbackModel, VercelAIAdapter. DO NOT USE for Claude
+  Agent SDK TypeScript agents or general LLM API calls.
+version: 0.2.0
 ---
 
 # PydanticAI Agent Development

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/refactoring-patterns/SKILL.md

@@ -1,14 +1,15 @@
 ---
 name: refactoring-patterns
 description: >-
-  This skill should be used when the user asks to "refactor this code",
-  "clean up this function", "extract a method", "reduce code duplication",
-  "fix code smells", "simplify this class", "break up this large function",
-  "apply design patterns", "remove dead code", "improve code structure",
-  or discusses code smells, refactoring techniques, extract function,
-  inline variable, feature envy, god class, or behavior-preserving
-  transformations.
-version: 0.1.0
+  Teaches behavior-preserving code transformations with a smell-detect,
+  transform, verify cycle and language-specific idioms for Python and
+  TypeScript. USE WHEN the user asks to "refactor this code", "extract a
+  method", "fix code smells", "reduce code duplication", "simplify this
+  class", "break up this large function", "clean up this function", or
+  "remove dead code", or works with god class, feature envy, data clump,
+  primitive obsession, or inline variable. DO NOT USE for adding new
+  features, fixing bugs, or performance optimization.
+version: 0.2.0
 ---
 
 # Refactoring Patterns

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/security-checklist/SKILL.md

@@ -1,14 +1,15 @@
 ---
 name: security-checklist
 description: >-
-  This skill should be used when the user asks to "check for security issues",
-  "audit this code for vulnerabilities", "scan for secrets", "review for
-  injection attacks", "check OWASP compliance", "find security bugs",
-  "detect hardcoded credentials", "review authentication logic",
-  "check for XSS", "audit dependencies for vulnerabilities",
-  or discusses security review, vulnerability scanning, OWASP Top 10,
-  secrets detection, SQL injection, command injection, or dependency auditing.
-version: 0.1.0
+  Provides defense-in-depth security review covering OWASP Top 10, secrets
+  detection, and dependency CVE scanning. USE WHEN the user asks to "check
+  for security issues", "scan for secrets", "audit dependencies for
+  vulnerabilities", "review for injection attacks", "check OWASP compliance",
+  "detect hardcoded credentials", or works with SQL injection, command
+  injection, pip-audit, npm audit, trivy, gitleaks. DO NOT USE for performance
+  profiling or general code quality reviews.
+version: 0.2.0
+allowed-tools: Bash, Read, Glob, Grep
 ---
 
 # Security Checklist

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/skill-building/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: skill-building
 description: >-
-  This skill should be used when the user asks to "build a skill", "write a
-  SKILL.md", "create a Claude Code skill", "design skill instructions",
-  "improve a skill description", "optimize skill content", "write effective
-  prompts for skills", or discusses skill authoring best practices, progressive
-  disclosure, or cross-vendor prompt engineering principles for Claude Code
-  plugins.
-version: 0.1.0
+  Guides Claude Code plugin skill creation covering SKILL.md structure,
+  description optimization, and progressive disclosure. USE WHEN the user
+  asks to "build a skill", "write a SKILL.md", "create a Claude Code skill",
+  "improve a skill description", "optimize skill content", "design skill
+  instructions", or works with skill authoring patterns or plugin directory
+  structure. DO NOT USE for application code or general prompt engineering.
+version: 0.2.0
 ---
 
 # Skill Building for Claude Code Plugins

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/sqlite/SKILL.md

@@ -1,13 +1,15 @@
 ---
 name: sqlite
 description: >-
-  This skill should be used when the user asks to "set up a SQLite database",
-  "use WAL mode in SQLite", "query SQLite with Python", "use better-sqlite3",
-  "add full-text search with FTS5", "store JSON in SQLite",
-  "use SQLite with Cloudflare D1", "write CTEs or window functions in SQLite",
-  or discusses SQLite pragmas, schema design, JSON1 extension, FTS5,
-  aiosqlite, or embedded database patterns.
-version: 0.1.0
+  Teaches SQLite development including WAL mode, FTS5 full-text search, JSON1
+  queries, and async Python integration with aiosqlite. USE WHEN the user asks
+  to "set up a SQLite database", "use WAL mode", "add full-text search with
+  FTS5", "store JSON in SQLite", "query SQLite with Python", "use
+  better-sqlite3", "use Cloudflare D1", "write CTEs or window functions", or
+  works with aiosqlite, better-sqlite3, PRAGMA configuration, STRICT tables,
+  expression indexes. DO NOT USE for PostgreSQL, MySQL, or other client-server
+  database systems.
+version: 0.2.0
 ---
 
 # SQLite Development

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/svelte5/SKILL.md

@@ -1,14 +1,13 @@
 ---
 name: svelte5
 description: >-
-  This skill should be used when the user asks to "build a Svelte component",
-  "create a Svelte app", "use Svelte runes", "set up a SvelteKit SPA",
-  "migrate from Svelte 4 to Svelte 5", "manage state with runes",
-  "add reactivity in Svelte", "use AI SDK with Svelte",
-  "add drag and drop to Svelte", "build charts with LayerCake",
-  or discusses Svelte 5 component patterns, snippets, $state, $derived,
-  $effect, $props, or SvelteKit routing.
-version: 0.1.0
+  Guides Svelte 5 development with runes, SvelteKit SPA configuration, and
+  component architecture. USE WHEN the user asks to "build a Svelte component",
+  "use Svelte 5 runes", "set up a SvelteKit SPA", "migrate from Svelte 4
+  to 5", "manage state with $state", "add drag and drop to Svelte", or works
+  with $state, $derived, $effect, $props, @ai-sdk/svelte, svelte-dnd-action.
+  DO NOT USE for Svelte 4 legacy codebases or React/Vue development.
+version: 0.2.0
 ---
 
 # Svelte 5 Development

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/team/SKILL.md

@@ -1,11 +1,17 @@
 ---
 name: team
 description: >-
-  This skill should be used when the user asks to "spawn a team",
-  "create a team of agents", "use a swarm", "work in parallel with agents",
-  "team up agents", "coordinate multiple agents", "split this across agents",
-  or needs to orchestrate parallel agent work using Claude Code Teams.
-version: 0.1.0
+  Guides agent team orchestration with TeamCreate, parallel teammate
+  spawning, task coordination, specialist agent selection, and
+  --teammate-mode configuration for concurrent workstreams. USE WHEN
+  the user asks to "spawn a team", "create a team of agents", "use a
+  swarm", "work in parallel", "coordinate multiple agents", "split this
+  across agents", "team up", or works with TeamCreate, SendMessage, and
+  multi-agent workflows. DO NOT USE for single-agent sequential tasks
+  where parallelism adds no value — a team requires 3+ independent
+  workstreams.
+version: 0.2.0
+disable-model-invocation: true
 ---
 
 # Agent Team Orchestration
@@ -113,6 +119,31 @@ TaskUpdate:
 - **Direct message:** `SendMessage` with `type: "message"` and `recipient: "test-writer"`
 - **Broadcast:** `SendMessage` with `type: "broadcast"` — use ONLY for critical team-wide issues
 - **Idle is normal:** Teammates go idle after each turn. This is expected. Send a message to wake them.
+- **Quality gate hooks:** TeammateIdle and TaskCompleted hooks run automatically. TeammateIdle checks for incomplete tasks (exit 2 → teammate keeps working); TaskCompleted runs the test suite (exit 2 → task stays open). See agent-system plugin hooks.
+
+**In-process mode keyboard shortcuts:**
+
+| Shortcut | Action |
+|----------|--------|
+| `Shift+Down` | Cycle through teammates |
+| `Ctrl+T` | Toggle task list |
+| `Enter` | View a teammate's session |
+| `Escape` | Interrupt teammate's current turn |
+
+> **Tip:** Use `claude --teammate-mode in-process` for per-session display mode override. Configure permanently via `teammateMode` in settings.json.
+
+### 5a. Plan Approval
+
+When `CLAUDE_CODE_PLAN_MODE_REQUIRED` is `true` (current setting), teammates run in read-only plan mode until the lead approves their plan.
+
+**Workflow:**
+1. Teammate enters plan mode → creates an implementation plan
+2. Lead receives `plan_approval_request` message with the plan
+3. Lead reviews the plan and sends `plan_approval_response` (approve or reject)
+4. On approval → teammate exits plan mode and implements
+5. On rejection → teammate stays in plan mode, revises, resubmits
+
+**Influencing plans:** Include criteria in the spawn `prompt` to shape what the lead should look for (e.g., "only approve plans that include test coverage", "reject plans that modify shared utilities without coordination").
 
 ### 6. Shutdown
 
@@ -151,6 +182,18 @@ Prefix with `agent-system:` when spawning (e.g., `agent-system:test-writer`).
 
 ---
 
+## Use Cases
+
+**Parallel code review** — split review criteria into independent domains (security, performance, test coverage). Each reviewer focuses on one lens, reducing blind spots.
+
+**Competing hypotheses** — adversarial investigation where teammates explore different theories about a bug or design decision. Each builds evidence for their hypothesis; lead synthesizes findings.
+
+**Cross-layer coordination** — frontend, backend, and tests each owned by a different teammate. Clear file ownership prevents conflicts; integration points are managed by the lead.
+
+**Research sweep** — parallel investigation of libraries, APIs, or approaches. Each researcher covers one option; lead compares findings and makes the selection.
+
+---
+
 ## Team Composition Examples
 
 | Purpose | Recommended Team |
@@ -180,6 +223,29 @@ Prefix with `agent-system:` when spawning (e.g., `agent-system:test-writer`).
 
 ---
 
+## Best Practices
+
+- **Give teammates enough context** — they don't inherit conversation history. The spawn `prompt` must be self-contained: include file paths, requirements, constraints, and project conventions.
+- **Size tasks appropriately** — too small = coordination overhead exceeds benefit; too large = work too long without check-ins. Aim for self-contained units producing clear deliverables, roughly 5-6 tasks per teammate.
+- **Wait for teammates to finish** — leads sometimes start implementing work that teammates are handling. If you notice this, redirect yourself to monitoring and coordination.
+- **Start with research and review** — for first-time team use, prefer tasks with clear boundaries that don't require code changes: reviewing PRs, researching libraries, investigating bugs.
+- **Monitor and steer** — check progress via `TaskList`, redirect failing approaches, synthesize findings. Unattended teams risk wasted effort.
+- **Avoid file conflicts** — break work so each teammate owns different files. Agents with `isolation: worktree` (test-writer, refactorer, doc-writer, migrator) get automatic file isolation via git worktrees.
+
+---
+
+## Limitations
+
+- **No session resumption** — `/resume` does not restore in-process teammates. Plan team work to complete in one session.
+- **Task status can lag** — teammates sometimes fail to mark tasks complete. Use `TaskList` to verify and `SendMessage` to prompt updates.
+- **One team per session** — clean up the current team (`TeamDelete`) before starting a new one.
+- **No nested teams** — teammates cannot create teams (TeamCreate/TeamDelete are disallowed for team members).
+- **Lead is fixed** — leadership cannot be promoted or transferred during a session.
+- **Permissions set at spawn** — all teammates inherit the lead's permission mode at spawn time.
+- **Split panes require tmux or iTerm2** — in-process mode uses the terminal; external split-pane workflows need tmux or iTerm2 with `it2` CLI.
+
+---
+
 ## Tool Reference
 
 | Tool | Purpose | Key Parameters |

package/.devcontainer/plugins/devs-marketplace/plugins/skill-engine/skills/testing/SKILL.md

@@ -1,13 +1,16 @@
 ---
 name: testing
 description: >-
-  This skill should be used when the user asks to "write tests for a FastAPI endpoint",
-  "test a Svelte component", "set up pytest fixtures for FastAPI",
-  "configure Vitest for SvelteKit", "mock dependencies in FastAPI tests",
-  "test SSE streaming endpoints", "write component tests with Testing Library",
-  "set up database fixtures for API tests", or discusses pytest, httpx AsyncClient,
-  Vitest, @testing-library/svelte, dependency overrides, or test fixtures.
-version: 0.1.0
+  Provides testing patterns for FastAPI endpoints and Svelte 5 components
+  using pytest and Vitest. USE WHEN the user asks to "write tests for a
+  FastAPI endpoint", "test a Svelte component", "set up pytest fixtures",
+  "configure Vitest for SvelteKit", "mock dependencies in tests", "test SSE
+  streaming endpoints", or works with pytest, httpx AsyncClient, Vitest,
+  @testing-library/svelte, MSW, pytest-anyio. DO NOT USE for general testing
+  theory unrelated to FastAPI or Svelte.
+version: 0.2.0
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep
+argument-hint: "[file or module]"
 ---
 
 # Testing (FastAPI + Svelte)

package/.devcontainer/plugins/devs-marketplace/plugins/spec-workflow/.claude-plugin/plugin.json

@@ -1,7 +1,6 @@
 {
 	"name": "spec-workflow",
 	"description": "Specification lifecycle management: creation, refinement, building, reviewing, updating, and auditing",
-	"version": "1.0.0",
 	"author": {
 		"name": "AnExiledDev"
 	}