RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Generate and validate a standalone sol3 research white paper end to end, export its Markdown and publication figures as an Arctic Fox PDF, and publish the accepted report to a secret GitHub Gist by default. Use when asked to test, smoke-test, or demonstrate research-report generation in solutions/sol3research.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Test any standalone solutions/sol1enhancer ticket-enhancer demo end to end: reset and seed its GitHub test tickets, run one poll, inspect live issues and diagnostics, post reviewer LGTM through the browser, and verify the ready or fail-closed exits. Use when asked to test, demo, smoke-test, or compare a sol1…
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Test a standalone Lab 2 ticket-implementer runtime end to end, from a fast local phase-fence regression to the shared T001 CRM fixture. Use for Deep Agents, Agent SDK, or a future runtime such as CrewAI without creating a shared loop engine.
RichardHightower/reliable-agentic-lab
Instructions file CodexOpenCode
AGENTS.md instructions for RichardHightower/reliable-agentic-lab, a project described as: Lab repo for Engineering Reliable Agentic AI Systems (Packt workshop, 29 August 2026). TicketCloser on a sample CRM.
RichardHightower/reliable-agentic-lab
Instructions file
Claude Code instructions for RichardHightower/reliable-agentic-lab, covering workshop shape (non-negotiable), what you may not do, what this repo actually is, if you are an agent reading this and work tracking policy.
RichardHightower/reliable-agentic-lab
Settings file Claude Code
Lab repo for Engineering Reliable Agentic AI Systems (Packt workshop, 29 August 2026). TicketCloser on a sample CRM.
RichardHightower/reliable-agentic-lab
Agent Claude Code
Investigates a ticket and the target app, and drafts an updated ticket body that fills its missing fields. Holds no write tool of any kind; its draft is the text of its final reply, for the enhancer-loop orchestrator to write to a candidate file and judge before it touches any real file.
RichardHightower/reliable-agentic-lab
Agent Claude Code
Reads one ticket file and reports which required fields for its kind have real content. Never writes anything, never grades its own draft.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
One poll-and-act step for the ticket enhancer. Enhances every open draft ticket that still needs work. A human LGTM is the only comment that marks a ticket ready. Use when invoked as /enhancer-loop, typically from task run or wrapped in /loop for repeated polling.
RichardHightower/reliable-agentic-lab
Plugin Claude Code
Same doer, judge, and loop skill as the Claude Code plugin, loaded by the Agent SDK.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Investigates a ticket and the target app, and drafts an updated ticket body that fills its missing fields. Returns the draft as text and saves nothing. Run through bin/role.sh, which puts this role in a read-only sandbox.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Reads one ticket file and reports which required fields for its kind have real content. Never writes anything, never grades its own draft. Run through bin/role.sh, which puts this role in a read-only sandbox.
RichardHightower/reliable-agentic-lab
Hook
Runs before the agent uses a tool, running an inline shell check. From RichardHightower/reliable-agentic-lab.
RichardHightower/reliable-agentic-lab
Hook
Runs after a tool call finishes, running an inline shell check. From RichardHightower/reliable-agentic-lab.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Rewrite a draft Northwind Field CRM ticket so it can pass the enhancer rubric. Use when delegated as the doer subagent.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Inventory which required fields a ticket currently has. Use when delegated as the judge subagent.
RichardHightower/reliable-agentic-lab
Agent
Writes the code that makes a failing test pass. Writes under app/ and nothing else, and cannot reach the tests.
RichardHightower/reliable-agentic-lab
Agent
Scores one attempt against the rubric and reports whether the ticket is done. Holds no write tool.
RichardHightower/reliable-agentic-lab
Agent
Turns one ready ticket into an ordered list of steps, one test step and one code step per acceptance criterion. Writes steps.jsonl and nothing else.
RichardHightower/reliable-agentic-lab
Agent
Writes the failing test for one acceptance criterion. Writes under tests/ and nothing else.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Make the failing tests pass without touching a test. Use when delegated as the code-implementer subagent.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Write steps.jsonl from the ready ticket. Use when delegated as the planner subagent.
RichardHightower/reliable-agentic-lab
Skill Claude CodeCodex
Write the failing tests the plan named. Use when delegated as the test-implementer subagent.
RichardHightower/reliable-agentic-lab
Agent
Returns Mermaid or PlantUML source for one figure, and simplifies it when the harness reports what the render lost. Holds no shell and no write tool.