AI & Agents
Agentic Workflows
GitHub Agentic Workflows (gh-aw) let you author an agent task as a markdown file — with YAML frontmatter — under .github/workflows/. GitHub compiles that source into a <name>.lock.yml GitHub Actions workflow, which is what actually runs.
CodeCargo's role with gh-aw today is inventory and observability, not execution or authoring — the platform detects and catalogs these files so admins get a consolidated view of them across the organization.
Detect + Catalog
This is the first phase of gh-aw support. CodeCargo classifies and surfaces metadata about agentic workflows, but does not yet apply policy or guardrails to them.
How Detection Works
During an organization workflow sync, CodeCargo scans for gh-aw source files (.md), their compiled .lock.yml output, and shared MCP configuration files (shared/*.md), pairing each source file with its compiled lock file by basename. Each file is classified into one of four types:
| Type | Description |
|---|---|
| Standard | A regular GitHub Actions workflow (not gh-aw) |
| Agentic source | The markdown source that defines an agentic workflow |
| Agentic lock | The compiled .lock.yml Actions workflow generated from a source file |
| Shared MCP | Shared MCP server configuration referenced by agentic workflows |
If a gh-aw file can't be parsed, it's still cataloged — marked as unparsed — rather than being dropped from the scan or failing it outright.
Governance Metadata
For each agentic workflow, CodeCargo extracts governance-relevant metadata from the frontmatter, including:
- Engine / model — which AI engine and model the workflow declares
- MCP servers — declared servers, their transport, read-only status, and allowed tools (secret key names only — CodeCargo never stores or displays secret values)
- Tool grants — which tools the workflow is permitted to use
- Safe outputs — declared safe-output configuration
- Network config — declared network access
- Timeout and concurrency — execution limits declared in the frontmatter
Any frontmatter fields CodeCargo doesn't yet recognize are preserved as opaque passthrough data rather than discarded.
Viewing Agentic Workflows
In the Workflows inventory (organization or project level), each workflow shows a Type badge indicating its classification. Use the All / Standard / Agentic filter above the table to narrow the list to just agentic source, lock, or shared MCP files.
Opening an agentic workflow's detail page adds an Agentic tab alongside the standard workflow detail tabs, showing the extracted engine, model, MCP server, tool grant, and network metadata for that workflow.
Guardrail Evaluation Scope
Agentic source files and shared MCP configuration are catalog-only entries, not executable Actions workflow YAML, so they're excluded from Workflow Compliance guardrail evaluation. Compiled agentic lock files are real Actions workflows and remain eligible for evaluation, same as standard workflows.