agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Display a comprehensive runtime environment report covering detected provider, available tools, AIWG version, and installed frameworks
$ npx -y skills add jmagly/aiwg --skill runtime-info --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/runtime-infoContext preview
The summary Claude sees to decide when to auto-load this skill.
Display a comprehensive runtime environment report covering detected provider, available tools, AIWG version, and installed frameworks
namespace: aiwg name: runtime-info platforms: [all] description: Display a comprehensive runtime environment report covering detected provider, available tools, AIWG version, and installed frameworks
You display a comprehensive runtime environment report — detected provider, available tools and permissions, AIWG version, installed frameworks, and relevant environment variables. Used by the Steward and orchestrators to determine provider routing and capability availability.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action | |---------|---------|--------| | Full report | "show runtime info" | Run `aiwg runtime-info` | | Provider check | "which provider is active?" | Run `aiwg runtime-info` → provider field | | Tool availability | "what tools are available?" | Run `aiwg runtime-info` → tools field | | Version check | "what version of AIWG is running?" | Run `aiwg runtime-info` → version field | | Framework check | "which frameworks are installed?" | Run `aiwg runtime-info` → frameworks field | | Environment dump | "show environment variables" | Run `aiwg runtime-info` → env field |
When triggered:
1. **Identify what the user wants**:
2. **Run the command**:
# Full runtime report aiwg runtime-info # Machine-readable (for orchestration / Steward routing) aiwg runtime-info --json
3. **Extract and present** the relevant section if the user asked about a specific aspect; present the full report otherwise.
The runtime-info report covers:
| Field | Description | |-------|-------------| | `provider` | Detected AI platform (claude-code, copilot, cursor, etc.) | | `aiwg_version` | Installed AIWG version (CalVer) | | `node_version` | Node.js runtime version | | `tools` | Available tool permissions (Read, Write, Bash, Glob, Grep, etc.) | | `frameworks` | Installed AIWG frameworks and their versions | | `env` | AIWG-relevant environment variables (AIWG_ROOT, AIWG_CONTEXT_WINDOW, etc.) | | `platform` | OS and architecture | | `cwd` | Current working directory |
**User**: "Show runtime info"
**Extraction**: Full report, no specific field
**Action**:
aiwg runtime-info
**Response**:
Provider: claude-code AIWG version: 2026.3.15 Node: v22.11.0 Platform: linux/x64 CWD: /mnt/dev-inbox/jmagly/aiwg Tools available: Read, Write, Edit, Bash, Glob, Grep Frameworks installed: sdlc-complete 2026.3.15 aiwg-utils 2026.3.15 Environment: AIWG_ROOT=/mnt/dev-inbox/jmagly/aiwg AIWG_CONTEXT_WINDOW=200000
**User (Steward)**: "Which provider is active so I can route this deployment?"
**Extraction**: Provider field only
**Action**:
aiwg runtime-info --json
**Response**: "Active provider is `claude-code`. Use `aiwg use sdlc --provider claude-code` for deployment."
**User**: "Do I have Bash access in this environment?"
**Extraction**: Tools field
**Action**:
aiwg runtime-info --json
**Response**: "Yes — Bash is listed in available tools. You also have Read, Write, Edit, Glob, and Grep."
**User**: "What frameworks are installed?"
**Extraction**: Frameworks field
**Action**:
aiwg runtime-info
**Response**: "2 frameworks installed: sdlc-complete (2026.3.15), aiwg-utils (2026.3.15). Run `aiwg list` for full framework details."
If the user's intent is ambiguous:
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing