restore-rehearsal
Validate and execute disposable Compose restore and candidate-upgrade drills.
Portable AI Agent Skills
Install inspectable instructions for recovery, Project Brain, universal inspection, change impact, evidence imports, release readiness, and extensions—without silently granting an agent new powers.
The bundle
Each skill is independently inspectable and can be installed only where it is needed.
Validate and execute disposable Compose restore and candidate-upgrade drills.
Build and query focused local project evidence without executing the project.
Initialize an existing project without overwriting its work or inventing commands.
Inspect web, native, CLI, API, code, documentation, and data surfaces with evidence.
Compare structural snapshots and choose verification based on affected connections.
Normalize external test, security, contract, and infrastructure evidence with provenance.
Detect local exports and prepare offline recovery proposals for review.
Check packages, compatibility, SBOMs, checksums, and bounded release gates.
Build typed, bounded, explicit-trust importers, analyzers, and recovery extensions.
Choose the project directory
The installer validates bundled files, refuses overwrites, and rolls back an incomplete multi-skill installation.
# Codex and agents using the common .agents directory
rehearse skill install .agents/skills --all
# Claude Code
rehearse skill install .claude/skills --all
# GitHub Copilot
rehearse skill install .github/skills --all
rehearse skill list --json
rehearse skill doctor --json
To install just Project Brain, replace --all with --name project-brain.
Capability boundary
Installing a skill supplies a workflow. It does not grant browser, desktop, Docker, network, deployment, secret, or repository-write access. The host agent and user remain responsible for authorization.
Outbound data
API keys, credentials, tokens, private keys, and backup contents must never be uploaded. Any other project information requires explicit consent for its destination and scope before it leaves the local project.
Local tool interface
Rehearse also exposes a bounded local MCP server for an existing brain. It uses standard input and output rather than a hosted service.
rehearse mcp serve project.rrbrain