session
Start an agentic session with pre-flight health checks, auto-repair, optional MCP injection, and provider launch
What this skill does
# AIWG Session Start a fully-prepared agentic session. Pre-flight checks run automatically: version currency, health diagnostics, and deployment verification. Issues are auto-repaired before launch. Pass `mcp` to inject configured MCP servers into the provider config first. ## Triggers Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description): - "start a session" → `aiwg session` - "launch claude" → `aiwg session --provider claude` - "start with mcp" → `aiwg session mcp` - "start fresh" → `aiwg session` (triggers full pre-flight) - "launch codex" → `aiwg session --provider codex` ## Trigger Patterns Reference | Pattern | Example | Action | |---------|---------|--------| | Default launch | "start a session" | `aiwg session` | | Explicit provider | "launch with codex" | `aiwg session --provider codex` | | With MCP | "start with my MCP servers" | `aiwg session mcp` | | MCP + provider | "launch cursor with MCPs" | `aiwg session mcp --provider cursor` | | Skip repair | "just launch, skip checks" | `aiwg session --no-repair` | ## Behavior When triggered: 1. **Resolve provider**: `--provider` flag → project config `providers[0]` → user config → `claude` 2. **Pre-flight** (auto-repair enabled by default): - Version check — updates aiwg if stale - Health check (`aiwg doctor`) — auto-repairs fixable issues - Deployment check — redeploys missing framework files - If repair fails: offers full reinstall + redeploy - If unresolvable: surfaces `aiwg feedback --type bug` 3. **MCP inject** (when `mcp` subcommand is used): ```bash aiwg mcp inject --provider <provider> ``` 4. **Launch**: - Spawnable providers (claude, codex, opencode): launches the binary directly - IDE providers (cursor, windsurf, copilot, factory, warp): prints ready instructions ## Examples ### Example 1: Default session **User**: "Start a session" **Action**: ```bash aiwg session ``` **Flow**: version check → doctor → deployment check → launch `claude` ### Example 2: Session with MCP **User**: "Start a session with my MCP servers" **Action**: ```bash aiwg session mcp ``` **Flow**: version check → doctor → deployment check → `aiwg mcp inject --provider claude` → launch `claude` ### Example 3: Specific provider **User**: "Launch with codex and inject MCPs" **Action**: ```bash aiwg session mcp --provider codex ``` ### Example 4: IDE provider (Cursor) **User**: "Set up my cursor session" **Action**: ```bash aiwg session --provider cursor ``` **Flow**: full pre-flight for cursor → deployment check for `.cursor/` → `aiwg mcp inject --provider cursor` (if mcp requested) → prints "Open Cursor in your project directory" ### Example 5: Skip repair **User**: "Just launch, skip the health checks" **Action**: ```bash aiwg session --no-repair ``` ## Clarification Prompts If the user's intent is ambiguous: - "Which provider should I launch? (claude, codex, opencode, cursor, ...)" - "Should I inject your configured MCP servers before launching?" ## References - @$AIWG_ROOT/src/cli/handlers/session.ts — Session command handler - @$AIWG_ROOT/src/cli/agent-spawn.ts — Provider launch map - @$AIWG_ROOT/docs/cli-reference.md — CLI reference (session section)
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.