Thomashighbaugh/agent-format-enforcer
skills/agent-format-enforcer/SKILL.md
Enforce the <Agent_Prompt> XML wrapper convention across all agent definition files. Scan, validate, and auto-fix non-compliant agents.
$ install --global
skillsauthnpx skillsauth add Thomashighbaugh/opencode agent-format-enforcerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 2:28 AM79.8s2 files scanned
SKILL.md
- name:
- agent-format-enforcer
- description:
- Enforce the <Agent_Prompt> XML wrapper convention across all agent definition files. Scan, validate, and auto-fix non-compliant agents.
- level:
- 2
Agent Format Enforcer
Enforce the <Agent_Prompt> XML wrapper convention on all agent .md files in agents/.
Standard Format
Every agent file MUST follow this structure:
---
description: Description of the agent's role
model: ollama/deepseek-v4-flash:cloud
mode: subagent
---
<Agent_Prompt>
<Role>
...agent instructions...
</Role>
</Agent_Prompt>
When to Use
- After creating or modifying an agent
- When onboarding agents from external sources
- During code review to catch format drift
- As part of
/project reviewor CI checks
Usage
# Scan all agents for compliance
/init-project doctor # delegates to this skill for agent check
# Or manually:
loadSkill agent-format-enforcer
What It Checks
| Check | Detail |
|-------|--------|
| YAML frontmatter | --- delimiters present |
| description | Required field |
| model | Required field |
| mode | Required field (subagent or primary) |
| <Agent_Prompt> | Opening wrapper tag present |
| <Role> | Sub-tag inside Agent_Prompt |
| </Agent_Prompt> | Closing wrapper tag present |
Script
scripts/check-agent-format.mjs — Standalone validation script that:
- Reads all
agents/*.mdfiles - Validates each against the standard format
- Reports per-agent compliance
- Exits 0 if all compliant, 1 if issues found
- Supports
--fixto auto-wrap non-compliant files
Related
agent-md-refactorskill — For larger-scale agent file restructuringhubs-doctorskill — Diagnostic health check that includes agent format validation
Related Skills
Thomashighbaugh/provision
tools
VerifiedTrustedCommunity
Analyze a codebase and auto-generate project-specific agents, skills, tools, and rules into .opencode/. Project wrappers inject deep project context into subagents for dramatically more effective AI assistance.
1SKILL.mdUpdated Jun 13, 2026
Thomashighbaugh/config-sync
development
VerifiedTrustedCommunity
Synchronize opencode.jsonc with the latest OpenCode config schema from Context7. Checks schema, detects drift, and updates config to remain compliant.
1SKILL.mdUpdated Jun 13, 2026
Thomashighbaugh/vectorize-context
development
VerifiedTrustedCommunity
Auto-maintained vector DB for semantic search over .opencode/context/ — zero manual triggers needed
1SKILL.mdUpdated Jun 9, 2026
Thomashighbaugh/orchestrate-router
tools
VerifiedTrustedCommunity
Natural language intent router — takes amorphous user requests and routes to the correct /orchestrate, /ideation, or /harvest-context subcommand
1SKILL.mdUpdated Jun 9, 2026