agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Manage AIWG behavior bundles that bind reactive directives and toolset configurations to specific agent types
$ npx -y skills add jmagly/aiwg --skill behavior --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/behaviorContext preview
The summary Claude sees to decide when to auto-load this skill.
Manage AIWG behavior bundles that bind reactive directives and toolset configurations to specific agent types
namespace: aiwg name: behavior platforms: [all] description: Manage AIWG behavior bundles that bind reactive directives and toolset configurations to specific agent types
You manage AIWG behavior bundles — YAML artifacts that bind reactive directives and toolset configurations to specific agent types. Behaviors are the newest AIWG artifact type and are primarily deployed to OpenClaw (`~/.openclaw/behaviors/`).
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action | |---------|---------|--------| | List behaviors | "list behaviors" | Run `aiwg behavior list` | | Show detail | "show behavior coding-strict" | Run `aiwg behavior info coding-strict` | | Apply behavior | "apply coding-strict to software-implementer" | Run `aiwg behavior apply coding-strict --to software-implementer` | | Remove behavior | "remove coding-strict from software-implementer" | Run `aiwg behavior remove coding-strict --from software-implementer` | | Inspect source | "where are behaviors stored?" | Check `agentic/code/*/behaviors/` and `~/.openclaw/behaviors/` |
When triggered:
1. **Extract intent**:
2. **Run the appropriate command**:
# List all available behaviors aiwg behavior list # Show details for a specific behavior aiwg behavior info <name> # Apply a behavior to an agent type aiwg behavior apply <name> --to <agent-type> # Remove a behavior from an agent type aiwg behavior remove <name> --from <agent-type>
3. **Understand behavior structure**: A behavior YAML bundle contains three sections:
4. **Know the storage locations**:
5. **Report results** — For `list`, show name and description for each. For `info`, show the full bundle structure. For `apply`/`remove`, confirm the change.
**User**: "What behaviors are available?"
**Extraction**: List request, no filter
**Action**:
aiwg behavior list
**Response**: "3 behaviors available:
---
**User**: "Show me what coding-strict does"
**Extraction**: Info request for `coding-strict`
**Action**:
aiwg behavior info coding-strict
**Response**: Shows the full YAML bundle — directives (require tests, no force push, enforce PR review), toolset (Read, Write, Edit, Bash with git restrictions), and any input variables.
---
**User**: "Apply no-external-calls to the software-implementer agent"
**Extraction**: Apply `no-external-calls` to `software-implementer`
**Action**:
aiwg behavior apply no-external-calls --to software-implementer
**Response**: "Applied `no-external-calls` to `software-implementer`. Deployed to `~/.openclaw/behaviors/software-implementer/no-external-calls.yaml`. Outbound HTTP is now blocked for that agent type."
---
**User**: "Remove coding-strict from the test-engineer"
**Extraction**: Remove `coding-strict` from `test-engineer`
**Action**:
aiwg behavior remove coding-strict --from test-engineer
**Response**: "Removed `coding-strict` from `test-engineer`. The behavior file has been deleted from `~/.openclaw/behaviors/test-engineer/`."
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