agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Display workspace status dashboard showing installed frameworks, deployments, artifact counts, and health indicators
$ npx -y skills add jmagly/aiwg --skill aiwg-status --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/aiwg-statusContext preview
The summary Claude sees to decide when to auto-load this skill.
Display workspace status dashboard showing installed frameworks, deployments, artifact counts, and health indicators
namespace: aiwg name: aiwg-status platforms: [all] kernel: true description: Display workspace status dashboard showing installed frameworks, deployments, artifact counts, and health indicators
You display a comprehensive workspace inventory dashboard: registry-installed frameworks and addons with versions, deployed provider artifact directories, project-local bundles, `.aiwg/` artifact counts by subdirectory, last sync time, and overall health indicators.
This skill is for **workspace inventory / install health**. It is not the cross-framework **project status** aggregator. If the user asks for `project-status`, "where are we?", "what is next?", or SDLC project progress, route through `aiwg discover "project status"` and load the `project-status` skill instructions instead.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action | |---------|---------|--------| | Full status | "show workspace status" | Run `aiwg status` | | Quick health | "is my workspace healthy?" | Run `aiwg status` | | Framework inventory | "what frameworks are installed?" | Run `aiwg status` | | Artifact counts | "how many requirements do I have?" | Run `aiwg status` | | Deployment check | "what's deployed to copilot?" | Run `aiwg status` | | Project progress | "project-status" / "where are we?" | Do **not** run `aiwg status`; use `aiwg discover "project status"` then `aiwg show skill project-status --first` |
When triggered:
1. **Distinguish from `doctor`**:
2. **Run the command**:
# Full status dashboard aiwg status
3. **What the dashboard shows**:
4. **Report the result** — present the dashboard output inline; highlight any WARN or ERROR indicators.
**User**: "Show me the workspace status"
**Extraction**: Full status request
**Action**:
aiwg status
**Response**:
AIWG Workspace Status ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Installed Frameworks (registry) sdlc-complete v2026.3.15 installed 2026-03-20 aiwg-utils v2026.3.15 installed 2026-03-20 voice-framework v2026.3.15 installed 2026-03-20 Provider Deployments claude-code .claude/ agents: 58 commands: 42 copilot .github/ agents: 58 prompts: 42 Project-local Bundles extensions 1 (agent-ops-control) .aiwg/ Artifacts intake/ 2 files requirements/ 7 files architecture/ 3 files planning/ 2 files risks/ 1 file testing/ 4 files security/ 1 file deployment/ 0 files working/ 5 files (temporary) reports/ 2 files Last sync: 2026-03-28 14:32 UTC Health: OK
**User**: "How is my workspace?"
**Extraction**: Health summary request
**Action**:
aiwg status
**Response**: Reports status dashboard as above, but with `Health: WARN — sdlc-complete may be outdated (last sync 8 days ago). Run \`aiwg sync --dry-run\` to check.`
**User**: "How many requirements files do I have?"
**Extraction**: Artifact count question; `status` provides this summary
**Action**:
aiwg status
**Response**: Points to the `.aiwg/ Artifacts` section of the output: "You have 7 files in `requirements/`."
**User**: "What's installed?"
**Extraction**: Framework inventory request
**Action**:
aiwg status
**Response**: Shows the Installed Frameworks (registry), Provider Deployments, and Project-local Bundles sections. If nothing is installed yet: "No frameworks installed. Run `aiwg use sdlc` to deploy the SDLC framework."
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