agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Lint @-mentions for style consistency and correctness
$ npx -y skills add jmagly/aiwg --skill mention-lint --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/mention-lintContext preview
The summary Claude sees to decide when to auto-load this skill.
Lint @-mentions for style consistency and correctness
namespace: aiwg name: mention-lint platforms: [all] description: Lint @-mentions for style consistency and correctness
<!-- AIWG-SKILL-CALLOUT --> > **Skill access pattern (post-kernel-pivot, 2026.5+)** > > Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via: > > ```bash > aiwg discover "<capability>" > aiwg show skill <name> > ``` > > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).
Validate @-mention style and fix common issues.
/mention-lint # Lint current directory /mention-lint --fix # Auto-fix fixable issues /mention-lint --strict # Exit with error on any issue /mention-lint --rules ML001,ML005 # Run specific rules only
| Option | Default | Description | |--------|---------|-------------| | --target | . | Directory to lint | | --fix | false | Auto-fix fixable issues | | --strict | false | Exit with error on any issue | | --rules | all | Comma-separated rule IDs |
| Rule | Description | Severity | Auto-fix | |------|-------------|----------|----------| | ML001 | @-mention path does not exist | error | no | | ML002 | @-mention uses wrong case | warning | yes | | ML003 | Missing required prefix (.aiwg/, src/, test/) | warning | yes | | ML004 | Uses deprecated path pattern | warning | yes | | ML005 | Invalid ID format (UC-NNN, ADR-NNN) | warning | yes | | ML006 | Duplicate @-mentions in same file | info | yes | | ML007 | @-mention in wrong section | info | no | | ML008 | Orphan @-mention (no back-reference) | info | no | | ML009 | Circular @-mention chain | warning | no | | ML010 | @-mention exceeds max depth (>3 hops) | warning | no |
src/services/auth/login.ts
L3: ML005 @.aiwg/requirements/UC-3-auth.md should be UC-003 (auto-fixable)
L5: ML001 @.aiwg/architecture/adrs/ADR-999.md does not exist
test/integration/auth.test.ts
L2: ML003 @auth/login.ts should be @$AIWG_ROOT/src/auth/login.ts (auto-fixable)
.aiwg/architecture/software-architecture-doc.md
L45: ML008 References @.aiwg/requirements/UC-005.md but no back-reference
Summary: 4 issues (1 error, 2 warnings, 1 info)
3 auto-fixable (run with --fix)Error: @.aiwg/requirements/UC-999.md → file not found
Not auto-fixable. Remove reference or create file.
Warning: @.aiwg/Requirements/UC-001.md should be @.aiwg/requirements/UC-001.md Fix: Correct case to match filesystem
Warning: @auth/login.ts should be @$AIWG_ROOT/src/auth/login.ts Fix: Add appropriate prefix
Warning: @requirements/UC-001.md should be @.aiwg/requirements/UC-001.md Fix: Update to current pattern
Warning: UC-3 should be UC-003 (3-digit format) Warning: ADR-5-auth should be ADR-005-auth Fix: Zero-pad numeric IDs
Info: @.aiwg/requirements/UC-001.md appears 3 times Fix: Remove duplicates, keep first occurrence
aiwg mention-lint [--target <dir>] [--fix] [--strict]
Lint @-mentions for: $ARGUMENTS
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