RichardHightower

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 Code

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

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 Claude Code

One of 2 in hooks.json

Runs before the agent uses a tool, running an inline shell check. From RichardHightower/reliable-agentic-lab.

RichardHightower/reliable-agentic-lab

Hook Claude Code

One of 2 in hooks.json

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 Claude Code

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 Claude Code

Scores one attempt against the rubric and reports whether the ticket is done. Holds no write tool.

RichardHightower/reliable-agentic-lab

Agent Claude Code

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 Claude Code

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 Claude Code

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.

RichardHightower/reliable-agentic-lab

Agent Claude Code

Scores a finished white paper against a fixed rubric and reports whether it is done. Holds no write tool.

RichardHightower/reliable-agentic-lab

Agent Claude Code

Answers one research question from primary sources and returns the atomic claims it found, each attached to a source and a quote. Writes nothing.

RichardHightower/reliable-agentic-lab

Agent Claude Code

Independently checks one claim against a source it finds itself. Never sees the original research. Writes nothing.

RichardHightower/reliable-agentic-lab

Agent Claude Code

Writes one section of the white paper from verified claims only. Writes under sections/ and nothing else. Assembly owns paper.md.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Produce an evidence-backed technical white paper from one topic. Plans the paper, researches each question from primary sources, verifies every claim against a second independent source, renders the figures, writes the sections, and checks the result before it ships.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Draw mermaid and plantuml sources for the concepts that need a picture.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Retrieve primary sources and report what they actually say.