agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions
$ npx -y skills add jmagly/aiwg --skill project-awareness --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/project-awarenessContext preview
The summary Claude sees to decide when to auto-load this skill.
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions
namespace: aiwg name: project-awareness platforms: [all] description: Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions
Comprehensive project context detection and state awareness.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
This skill provides rich project context awareness including:
When triggered, this skill:
1. **Detects project type**:
2. **Identifies AIWG state**:
3. **Parses team configuration**:
4. **Loads recent activity**:
5. **Builds context object**:
| Natural Language | Action | |------------------|--------| | "Where are we?" | Check phase status, recent activity | | "What's next?" | Identify pending tasks, next milestone | | "Project status" | Full status report | | "Current phase" | Phase name + completion percentage | | "Ready to transition?" | Gate criteria check | | "What's blocking us?" | Risk register + blockers | | "How long until..." | Milestone progress estimate | | "Who owns..." | Team and agent assignments |
{
"project": {
"name": "my-project",
"type": "application",
"subtype": "web-api",
"root": "/path/to/project",
"description": "From package.json or README"
},
"tech_stack": {
"languages": ["typescript", "python"],
"runtime": "node",
"framework": "express",
"package_manager": "npm",
"database": "postgresql",
"testing": "vitest",
"ci_cd": "github-actions"
},
"aiwg": {
"installed": true,
"frameworks": ["sdlc-complete"],
"addons": ["aiwg-utils", "voice-framework"],
"phase": "elaboration",
"iteration": 3,
"agents_deployed": 45,
"commands_deployed": 38
},
"team": {
"members": [
{"name": "John", "role": "tech-lead", "agent": "architecture-designer"}
],
"agent_assignments": {
"architecture-designer": "John",
"test-architect": "Jane"
}
},
"activity": {
"current_branch": "feature/user-auth",
"recent_commits": [...],
"open_prs": [...],
"modified_artifacts": [...],
"last_gate_check": "2025-12-05"
},
"artifacts": {
"total": 24,
"by_status": {
"draft": 5,
"review": 3,
"baselined": 16
},
"recent": [...]
},
"recommendations": [
"Complete SAD review (2 reviewers pending)",
"Run gate-check for Elaboration exit",
"Update risk register (7 days stale)"
]
}Phase: [Current Phase] ([X]% complete) Iteration: [N] of [Total] Next Milestone: [Milestone Name] - [Date/Status] Blockers: [Count] ([List if < 3])
## Project: [Name] Phase: [Phase] | Iteration: [N] Started: [Date] | Target: [Date] ### Completion - Requirements: [X]% - Architecture: [X]% - Implementation: [X]% - Testing: [X]% ### Active Work - [Task 1] - [Owner] - [Status] - [Task 2] - [Owner] - [Status] ### Blockers/Risks - [Risk 1] - [Severity] - [Mitigation] ### Next Steps 1. [Action 1] 2. [Action 2]
| Indicator | Project Type | |-----------|-------------| | package.json + src/index.ts | Node.js application | | package.json + lib/ | Node.js library | | setup.py or pyproject.toml | Python package | | Cargo.toml | Rust project | | go.mod | Go module | | pom.xml | Java Maven project | | turbo.json or lerna.json | Monorepo |
| Files | Framework | |-------|-----------| | next.config.js | Next.js | | angular.json | Angular | | vite.config.ts | Vite | | django, manage.py | Django | | express in package.json | Express | | fastapi in requirements | FastAPI |
| Location | Information | |----------|-------------| | .aiwg/ | AIWG artifacts directory exists | | .aiwg/config/registry.json | Installed frameworks | | .aiwg/planning/phase-plan-*.md | Current phase | | .aiwg/planning/iteration-*.md | Current iteration | | .claude/agents/ | Deployed agents | | .claude/commands/ | Deployed commands |
| Artifacts Present | Likely Phase | |-------------------|--------------|
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