Real Skill packageSource verifiedClawHub registry

Agent Factory

Autonomous sub-agent factory for OpenClaw: recurring workload detection, sandboxed synthesis, 4D benchmark evaluation vs generalist baseline, dynamic vector routing, and lifecycle drift monitoring.

Identity and source

Publisher attributionSélimregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 66% rule confidence
Package forminstruction with code59 recorded files
Canonical sourceClawHub registryclawhub:samajesteduroyaume:agent-factory-2
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/31/2026.claude/skills/agent-factory

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/31/2026.agents/skills/agent-factory

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/31/2026skills/agent-factory

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @samajesteduroyaume/agent-factory-2
clawhub inspect @samajesteduroyaume/agent-factory-2 --version 0.1.0

Security evidence

SkillVetAI static result: medium signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
partial text content
Files
40 / 59 inspected as text
Checked
8/31/2026, 5:39:44 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
mediumPrompt-override language requires reviewskills/agent-factory/scripts/red_team_fuzzer.py:16 · confidence 62%Ignore all previous instructions
6 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • external write action — automatically inferred
9 dependency and API indicators
  • pypi: fastapi >=0.100.0
  • pypi: uvicorn >=0.22.0
  • pypi: pydantic >=2.0.0
  • pypi: pytest >=7.0.0
  • api: api.openai.com
  • api: clawhub.ai
  • api: fonts.googleapis.com
  • api: github.com
  • api: img.shields.io
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/30/2026, 5:16:09 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:7fdda6b2d977dd8fad96062c8a9db28a483b74a4d279cc05ed4e56d2a41a1d82
Show up to 30 recorded paths
  • .github
  • .github/workflows
  • .github/workflows/clawhub-publish.yml
  • .gitignore
  • clawhub.json
  • LICENSE
  • README.fr.md
  • README.md
  • requirements.txt
  • skill-card.md
  • SKILL.md
  • skills
  • skills/agent-factory
  • skills/agent-factory/clawhub.json
  • skills/agent-factory/dashboard
  • skills/agent-factory/dashboard/app.py
  • skills/agent-factory/dashboard/static
  • skills/agent-factory/dashboard/static/app.js
  • skills/agent-factory/dashboard/static/index.html
  • skills/agent-factory/dashboard/static/style.css
  • skills/agent-factory/data
  • skills/agent-factory/data/alerts_history.jsonl
  • skills/agent-factory/data/circuit_breakers.json
  • skills/agent-factory/data/exports
  • skills/agent-factory/data/exports/subagent_invoice_extraction-v1.0.0.clawbundle.tar.gz
  • skills/agent-factory/data/finops_summary.json
  • skills/agent-factory/data/semantic_cache.json
  • skills/agent-factory/data/task_telemetry.jsonl
  • skills/agent-factory/data/training_datasets
  • skills/agent-factory/data/training_datasets/dpo_invoice_extraction.jsonl

Source changelog

Initial release of agent-factory for OpenClaw. - Enables autonomous creation, benchmarking, and dynamic routing to specialized sub-agents under orchestrator control. - Implements 5-phase pipeline: workload detection, sandboxed synthesis, 4D evaluation, mesh registration, and lifecycle monitoring. - Strict guardrails: sub-agents are ephemeral, sandboxed, tool-limited, and cannot act until passing rigorous benchmarks versus baseline. - Continuous telemetry logging, cluster detection, and automated rollback/drift handling. - Provides CLI tools for telemetry, synthesis, evaluation, routing, and lifecycle auditing.