v6.3.0

snarktank/ralphv6.3.0Aug 12, 2026by obra

AI Summary

This release enhances Subagent-Driven Development by resolving plan conflicts without stalling and introduces support for Devin CLI and Hermes Agent. It also improves workflow stability by preventing untracked file deletion during worktree removal and optimizes Codex performance.

Key Highlights

  • Added Harness support for Devin CLI, Hermes Agent, and Grok Build CLI.
  • Controllers no longer stall on non-catastrophic plan conflicts; they now record rulings and continue.
  • Worktree removal now asks for confirmation instead of force-deleting untracked files.
  • Codex performance is improved with event-driven waits and explicit spawn pin models.
  • The 'Ceremony' now scales to task size, skipping rituals for small tasks.

New Features

  • Devin CLI integration with automatic skill triggering at session start.
  • Hermes Agent integration with native skill loader and bootstrap on first turn.
  • Adaptive 'Ceremony' logic that classifies tasks as spike, bounded, or architectural.
  • Conflict scanning ledger to record plan checks instead of just asserting cleanliness.
  • Batching of same-shape micro-tasks for reduced subagent costs.
  • Plans now carry a 'Spec:' pointer for resolving conflicts against design.

Full Release Notes


### Harness Support

- **Devin CLI**: `devin plugins install obra/superpowers` now works, and skills auto-trigger at session start. (#1995)
- **Hermes Agent**: install from a git clone; skills register with Hermes' native loader and the bootstrap loads on the first turn. (#1922, #2025)
- **Grok Build CLI** added to the install docs. (#1919)

### Brainstorming

- **Ceremony now scales to the task.** Requests are classified as spike, bounded, or architectural; small tasks skip the two-document ritual. Every path still stops for your approval before implementation. (#2063)

### Subagent-Driven Development

- **Controllers no longer stall on plan conflicts.** Non-catastrophic conflicts and ambiguities get a recorded ruling and work continues; only destructive or irreversible actions still stop for a human. One donated session had sat blocked for almost nine hours on a question the controller could have decided. (#2077)
- **The pre-dispatch conflict scan records its checks in the ledger** instead of just asserting the plan is clean. (#2080)
- **Small same-shape tasks batch into one dispatch**, cutting subagent cost sharply on micro-task plans; batch reviews verify every file in the brief made it into the diff. (#2078)
- **Implementers and reviewers may not spawn their own subagents**, which was producing duplicate reviews. (#2059)
- **Plans carry a `Spec:` pointer** and SDD reads the spec at setup, so plan conflicts get resolved against the design instead of guessed at. (#2086)
- Reviewers re-read evidence they find illegible instead of re-running the test suite (#2089), and circuit-breaker rulings now show up in the Finish report.

### Codex

- Subagent waits are event-driven instead of poll-heavy, spawns pin model and reasoning effort explicitly, and the multi-agent reference is corrected against Codex source. (#2060, #2061, #2062)

### Finishing a Development Branch

- **Worktree removal no longer destroys untracked files.** When `git worktree remove` refuses because the tree holds uncommitted work, the skill stops, names the files, and asks — instead of reaching for `--force`. (#2016, #1223, #2024)

### Fixes

- `render-graphs.js` in writing-skills works on Windows.
- Corrected Copilot CLI backgrounding guidance for Windows. (#1929, #2006)
- `bump-version.sh` covers the Hermes manifest.

### Documentation

- README: added a table of contents and reorganized Getting Started.