Improve README with clearer value prop, trade-offs, and architecture flow#4
Improve README with clearer value prop, trade-offs, and architecture flow#4AaronGoldsmith merged 6 commits intomainfrom
Conversation
…flow - Add "when Mobius is worth it" section with honest trade-off framing - Add prerequisites section with mandatory vs optional API keys - Show all three bootstrap options (API, Claude Code, scout) upfront - Add Trade-off column to "Why Mobius?" table - Replace architecture file listing with orchestrator flow diagram - Add context and caveats to cost table (token range, date, local embeddings) - Note env-overridable vs code-only config options - Remove duplicate `mobius train` command entry Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 9ec65853fb
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
There was a problem hiding this comment.
Pull request overview
Updates the project README to present Mobius with clearer positioning, prerequisites, trade-offs, and a higher-level architecture walkthrough aimed at setting more accurate expectations for users evaluating the framework.
Changes:
- Adds “When Mobius is worth it” and a prerequisites section clarifying setup paths.
- Reworks “Why Mobius?” to include explicit trade-offs alongside benefits.
- Replaces the architecture file-tree listing with an orchestrator flow diagram and expands cost guidance.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
…ount - Fix cost date from March 2025 to March 2026 - Add `mobius agent export` to commands list (exists in CLI but was undocumented) - Fix scout demo showing 4 agents when --count 5 was requested Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix scout bootstrap: "free API cost" → "~$0.50" (uses Opus API) - Add scout row to cost table - Clarify Claude Code note: CLI commands still require API keys - Standardize subscription naming to "Pro/Team" everywhere - Clarify Anthropic needed for default judge panel (not just "recommended") - Change "rate limiting" to "concurrency control" (semaphore in swarm.py) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Covers Pro, Max, and Team without needing updates as plans change. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Updates the project README to set clearer expectations about when Mobius is a good fit, explain setup paths (paid API vs. Claude Code skills), and replace the file-tree architecture listing with a higher-level execution flow explanation.
Changes:
- Add “When Mobius is worth it” and expand quick start with explicit prerequisites and bootstrap options.
- Add trade-offs to the “Why Mobius?” section and update commands list.
- Replace architecture file listing with an orchestrator flow diagram and refresh cost/configuration explanations.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
…uirements, and trade-off wording Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Summary
mobius traincommand entryMotivation
Ran a Mobius competition (
/mobius-run) asking agents to critique the README. The Skeptical Engineer (Claude Haiku) won unanimously across all 3 judges (Opus, Gemini Pro, GPT-4o) with a focus on transparency and intellectual rigor — the core theme was "under-promise, deliver well."Test plan
🤖 Generated with Claude Code