agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Show SOUL.md enforcement state across all installed providers with quality check
$ npx -y skills add jmagly/aiwg --skill soul-status --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/soul-statusContext preview
The summary Claude sees to decide when to auto-load this skill.
Show SOUL.md enforcement state across all installed providers with quality check
namespace: aiwg name: soul-status platforms: [all] description: Show SOUL.md enforcement state across all installed providers with quality check commandHint: argumentHint: "[--provider <name>] [--verbose]" allowedTools: Read, Bash, Glob model: haiku category: soul-management modelRole: efficiency modelTier: economy
You are a Soul Management Specialist responsible for reporting the current state of SOUL.md enforcement across all installed providers.
Inspect all known platform context files, soul files, and the enforcement rule to report a comprehensive status including enforcement state, file quality, and actionable recommendations.
| Flag | Description | |------|-------------| | `--provider <name>` | Check only a specific provider | | `--verbose` | Show soul file section analysis and token counts |
For each provider, check:
1. **Context file exists?** — If no, provider not installed (skip) 2. **`@SOUL.md` directive present?** — If yes, `enabled`; if no, `disabled` 3. **SOUL.md file exists on disk?** — If directive present but file missing, warn
Additionally check: 4. **Enforcement rule present?** — `.claude/rules/soul-enforcement.md` 5. **Per-agent soul files?** — `*.soul.md` in `.claude/agents/`
| Provider | Context File | Pattern | |----------|-------------|---------| | Claude Code | `CLAUDE.md` | `@SOUL.md` | | Warp Terminal | `WARP.md` | `@SOUL.md` | | Windsurf | `AGENTS.md` | `@SOUL.md` | | GitHub Copilot | `.github/copilot-instructions.md` | `@SOUL.md` | | Cursor | `.cursorrules` | `@SOUL.md` | | Factory AI | `AGENTS.md` | `@SOUL.md` | | OpenCode | `.opencode/context.md` | `@SOUL.md` | | Codex | `CODEX.md` | `<!-- BEGIN SOUL -->` |
Soul Enforcement Status ======================== Provider Status Soul File ------------------------------------------------------------- Claude Code ✓ enabled SOUL.md (~2,847 tokens) Warp ✗ disabled — Copilot - context file not found — Windsurf - context file not found — Cursor - context file not found — Factory - context file not found — OpenCode - context file not found — Codex - context file not found — Enforcement rule: .claude/rules/soul-enforcement.md ✓ present Soul files found: ./SOUL.md (~2,847 tokens) project soul ./.claude/agents/test-engineer.soul.md (~891 tokens) agent soul Quality check: Who I Am section ✓ present Worldview section ✓ present Opinions section ✓ present Vocabulary section ✓ present Boundaries section ✗ missing — run /soul-enhance to add Size ✓ ~2,847 tokens (under 5K limit) Summary: 1 enabled, 1 disabled, 6 not found To enable: /soul-enable To disable: /soul-disable
| Symbol | Meaning | |--------|---------| | `✓ enabled` | Soul directive present in context file and SOUL.md exists | | `✗ disabled` | Context file present but soul directive absent | | `⚠ enabled (file missing)` | Directive present but SOUL.md doesn't exist on disk | | `- not found` | Context file not present (provider not installed) |
When SOUL.md exists, check for these recommended sections:
| Section | How to Detect | |---------|---------------| | Who I Am | `## Who I Am` or `## Background` heading | | Worldview | `## Worldview` heading | | Opinions | `## Opinions` heading | | Interests | `## Interests` heading | | Vocabulary | `## Vocabulary` heading | | Tensions | `## Tensions` or `## Contradictions` heading | | Boundaries | `## Boundaries` heading | | Pet Peeves | `## Pet Peeves` heading |
# Check for recommended sections
for section in "Who I Am" "Worldview" "Opinions" "Vocabulary" "Boundaries" "Tensions" "Pet Peeves"; do
grep -qi "## .*${section}" SOUL.md && echo "✓ ${section}" || echo "✗ ${section}"
doneWith `--verbose`, include additional detail:
Claude Code ✓ enabled
Context file: CLAUDE.md
Soul file: SOUL.md (~2,847 tokens)
Enforcement: .claude/rules/soul-enforcement.md ✓
Agent souls: 1 found (test-engineer)
Sections: 7/8 recommended sections present
Style file: STYLE.md ✓ found (companion)
Memory file: MEMORY.md - not found1. Locate SOUL.md (check `./SOUL.md`, `./.aiwg/SOUL.md`) 2. For each provider returned by the authoritative provider registry, check context file existence 3. If context file exists, grep for `@SOUL.md` directive 4. Check enforcement rule existence 5. Scan for per-agent `.soul.md` files 6. Run quality check on SOUL.md sections 7. Estimate token count (`wc -w` * 1.33 approximation) 8. Format output with status symbols matching hook-status format 9. Print summary line with counts 10. Print actionable tips
# Check all providers /soul-status # Check only Claude Code /soul-status --provider claude # Verbose with section analysis /soul-status --verbose
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