joaofnds

Rehearse — Development skill for Claude Code

Development community

Benchmark and improve coding-agent instructions with real Claude Code sessions, stage replay, and graded evidence.

How to install Rehearse

This entry records only its repository, not the path inside it, so there is no exact command to give. Open joaofnds/rehearse and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Rehearse does

Benchmark and improve coding-agent instructions with real Claude Code sessions, stage replay, and graded evidence.

Alternatives in Development

Battle — Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line 3.6k ★
Claude Code Agent Farm — A powerful orchestration framework that runs multiple Claude Code (cc) sessions in parallel to systematically 704 ★
Alethe Agents — A local-first desktop workspace for running, organizing, and resuming multiple coding agents and shells with r 511 ★

README

Rehearse

Find out whether changing your coding agent's instructions actually helps.

Rehearse runs a fixed task through the real Claude Code CLI, records the instructions and evidence, and grades the result. You can replay a workflow stage after editing a skill, or repeat a session to see how much its results vary. The goal is a debugger and regression suite for an engineer's instruction corpus: project guidance, skills, output styles, and agent definitions.

For example, a shorter instruction might produce a better reply once. Rehearse helps you inspect that attempt, repeat the task, and compare quality with cost before deciding the instruction earned its place.

**Early development.** The CLI is usable, and a local browser UI reads recorded evidence. Some workflows still depend on the maintainer's environment. Session confirmation groups can feed multi-case comparisons alongside stage and pipeline groups. See [current state and priorities](docs/status.md) before planning an experiment.

How it works

Choose a case + instructions + model
                  |
          Run the real agent
                  |
       Grade and retain evidence
                  |
       Inspect → edit → run again
                  |
     Confirm with repeated trials

Session cases run one prompt in a temporary directory, optionally with fixture files or a captured conversation prefix. Deterministic checks grade the reply and tool transcript.
Pipeline cases run a declared sequence of skills against a target Git repository. A Product Owner answers questions, independent Judges grade each stage, and checkpoints let you replay a stage without rerunning its predecessors.
Confirmation runs repeat frozen inputs and report reliability and resource usage. A single attempt is debugging evidence, not proof of improvement.

The current provider is Claude Code. This is a local tool using your credentials and agent environment, with records under `.benchma