agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Regenerate OpenCode context file (.opencode/context.md) with AIWG framework content
$ npx -y skills add jmagly/aiwg --skill aiwg-regenerate-opencode --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/aiwg-regenerate-opencodeContext preview
The summary Claude sees to decide when to auto-load this skill.
Regenerate OpenCode context file (.opencode/context.md) with AIWG framework content
namespace: aiwg name: aiwg-regenerate-opencode platforms: [all] description: Regenerate OpenCode context file (.opencode/context.md) with AIWG framework content commandHint: argumentHint: "[--no-backup] [--dry-run] [--full-inject] [--migrate]" allowedTools: Read, Write, Edit, Bash, Glob model: sonnet category: context-regeneration modelRole: coding modelTier: standard
Regenerate the `.opencode/context.md` file for OpenCode integration. Performs an **intelligent merge** — preserving team-written content while updating AIWG context.
**Team content is preserved. AIWG content is updated. Hook file approach used when supported.**
| Flag | Description | |------|-------------| | `--no-backup` | Skip creating backup file | | `--dry-run` | Preview changes without writing | | `--full-inject` | Inject full content directly into context.md (legacy/compatibility mode) | | `--migrate` | Migrate existing full-injection to hook file approach |
By default, this command uses the hook file architecture:
1. Generate `AIWG-opencode.md` with AIWG framework content 2. Add `@AIWG-opencode.md` directive to `.opencode/context.md`
**Note**: OpenCode's support for `@file` directives is not yet confirmed. If the `@` directive is not supported, use `--full-inject` as a fallback. See #444 for status.
Unless `--no-backup` specified, create `.opencode/context.md.backup-{YYYYMMDD-HHMMSS}`.
Read `.opencode/context.md` if it exists and categorize:
Check whether existing `.opencode/context.md` uses a hook file directive:
grep -q "@AIWG-opencode.md" .opencode/context.md && echo "hook approach" || echo "full inject or fresh"
Generate the hook file content from installed framework manifests (same as `aiwg hook-regenerate --provider opencode`).
**If `--full-inject`**: Skip hook file generation, embed content directly.
**Hook approach** (default): 1. Write `AIWG-opencode.md` with generated content 2. Update `.opencode/context.md`: preserve team content + add `@AIWG-opencode.md` directive
**Full inject** (`--full-inject`): 1. Embed full AIWG content in `.opencode/context.md` between markers:
<!-- BEGIN AIWG --> [content] <!-- END AIWG -->
OpenCode Context Regenerated ============================= Backup: .opencode/context.md.backup-20260322-190000 Hook file: AIWG-opencode.md (312 lines, written) Context file: .opencode/context.md updated @AIWG-opencode.md directive added Team content preserved: 14 lines
OpenCode's support for `@file` includes within `.opencode/context.md` is currently unverified (see #444). If you encounter issues with AIWG context not loading:
# Fall back to full injection /aiwg-regenerate-opencode --full-inject
# Default (hook file approach) /aiwg-regenerate-opencode # Full injection (compatibility mode) /aiwg-regenerate-opencode --full-inject # Preview without writing /aiwg-regenerate-opencode --dry-run # Migrate from full inject to hook file /aiwg-regenerate-opencode --migrate
| Command | Regenerates | |---------|-------------| | `/aiwg-regenerate` | Auto-detect and delegate | | `/hook-status` | Check hook state | | `/hook-regenerate --provider opencode` | Rebuild hook file only | | `/migrate-hook --provider opencode` | Migrate full inject to hook |
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