human agent
Agent development, migration, and compliance CLI
Develop, migrate, and validate HUMΛN agents from the terminal.
Migration workflow
# 1. Scan for existing agents
human agent detect .
# 2. Scaffold a HUMΛN wrapper (preserves your source file)
human agent import --from=langchain src/my-agent.py --output ./migrated
# 3. CI compliance gate
human agent check ./migrated/src/my-agent-agent.ts --strict
Install IDE migration skills: human setup cursor --agent-kit.
Framework guides: Migration hub.
---
human agent detect
Scan a file or directory for agent sources and frameworks.
| Option | Description |
|---|---|
[path] | File or directory (default: .) |
--json | JSON array for CI |
--summary | One-line counts only |
---
human agent import
Two modes:
--from= scaffolds a HUMΛN handler, install-manifest.ts, prompts/system.md, tests, and README-migration.md.WorkflowManifestV1).Agent migration options
| Option | Description |
|---|---|
--from | openai, langchain, crewai, ecc, n8n, agentfield, custom, auto |
--output | Output directory (default: ./migrated) |
--preserve-prompts | Copy inline system prompts into prompts/system.md |
Workflow import options
| Option | Description |
|---|---|
--local | Write manifest locally (no API) |
--platform | Force platform detection |
--platforms | List supported workflow platforms |
human agent check
Run the 9-point HUMΛN Agent Compliance Checklist (static analysis).
| Option | Description |
|---|---|
--strict | Treat PARTIAL as FAIL |
--json | { score, overall, checks: [...] } |
--fix | Suggest TODO markers (dry-run) |
--apply | Write --fix suggestions |
Checklist:
@human/core) ctx.prompts.load() ctx.llm.complete({ prompt }) ctx.delegation.scope) withProvenanceContext + ctx.provenance.log() ctx.memory ctx.call) handler({ execute }) from @human/agent-sdk ---
human agent docs
Print documentation URLs for migration topics (migration, openai, langchain, sdk, …).
human agent ctx
Print the ExecutionContext (ctx.*) surface reference for handlers.
---
Other agent commands
| Command | Description |
|---|---|
human agent init | Scaffold a new agent project |
human agent dev | Local dev server |
human agent deploy | Deploy to HUMΛN Cloud |
human agent catalog | Browse marketplace agents |
Marketplace publish checklist
Before human marketplace publish:
pnpm prompts:lint (Defense Baseline on system prompts)human marketplace review --prompts-dir . (Prompt Safety Certification)POST /v1/marketplace/review with bundle path for checks 1–13 + 15Listings expose prompt_certification (hashes + trust boundary) — not prompt bodies. See marketplace CLI docs.