Builds and installs new agents end-to-end: design, code, package, gate, install.
EnglishAnalyzes failed sessions with code-level root causes and files scoped GitHub issues.
EnglishTranslates natural-language governance intent into structured constitutional amendment proposals.
EnglishHandles multi-step human-in-the-loop credential ceremonies (OAuth, identity verification, manual token entry) after the planner starts onboarding.
EnglishValidation and testing autonomous agent (operator-invokable sealed-network evaluation).
EnglishSystem-tier red-team agent: proposes adversarial attack patterns the sentinel should catch. Structurally separated from the sentinel — never authors eval suites targeting itself.
EnglishFrozen baseline sentinel — runs deterministic-only checks. The gateway-side SentinelRunner executes the checks without LLM calls; the llmconfig here is a thin orchestrator fallback for structured output formatting only.
EnglishStatic code review for artifact correctness, credential flow, and behavioral contracts.
EnglishFinds installed agents that match a given task intent using agentlist + LLM reasoning.
Uncertain
AGENT SKILLS ATLASIncludes Agent Factory.default, Code Issue Proposer.default, Governance Author.default, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Agent Factory.default
Builds and installs new agents end-to-end: design, code, package, gate, install.
Code Issue Proposer.default
Analyzes failed sessions with code-level root causes and files scoped GitHub issues.
Governance Author.default
Translates natural-language governance intent into structured constitutional amendment proposals.
Registration.default
Handles multi-step human-in-the-loop credential ceremonies (OAuth, identity verification, manual token entry) after the planner starts onboarding.
Sealed Evaluator.default
Validation and testing autonomous agent (operator-invokable sealed-network evaluation).
Security Redteam.default
System-tier red-team agent: proposes adversarial attack patterns the sentinel should catch. Structurally separated from the sentinel — never authors eval suites targeting itself.
Security Sentinel Baseline.default
Frozen baseline sentinel — runs deterministic-only checks. The gateway-side SentinelRunner executes the checks without LLM calls; the llmconfig here is a thin orchestrator fallback for structured output formatting only.
Static Evaluator.default
Static code review for artifact correctness, credential flow, and behavioral contracts.
Discovery.default
Finds installed agents that match a given task intent using agentlist + LLM reasoning.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Agent Factory.default skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: Apache-2.0. The author’s terms apply.