// Use after writing or editing a plan file, after exiting plan mode, or when asked "why did you choose this?" — surfaces decisions, risks, and blind spots before implementation.
Automatic tool discovery across 19 sources — INVOKE before planning, before adding dependencies, or when looking for tools to discover relevant skills, plugins, and MCP servers
Continuous learning — INVOKE after sessions with many errors or corrections to record patterns and improve rules, hooks, and skills
Session history search — INVOKE before planning, before web research, after errors, or when looking for past conversation content. Use INSTEAD of manually grepping .jsonl session files.
Cross-session memory - save insights after research, restore context at session start. Reduces re-exploration and prevents token waste.
File checkpoint and recovery — auto-quicksaves before destructive commands, INVOKE before implementing a plan or starting risky multi-file changes. Also use when user asks to undo changes or compare current state to a prior checkpoint.
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
| name | claude-augur |
| description | Use after writing or editing a plan file, after exiting plan mode, or when asked "why did you choose this?" — surfaces decisions, risks, and blind spots before implementation. |
Surface plan reasoning as scannable inline abstracts. Decisions, risks, discoveries, recommendations — visible at a glance.
| Tool | Purpose |
|---|---|
augur_explain | Extract plan structure and return a template for inline rendering |
augur_explain(plan_path: "/path/to/plan.md")[FILL] markersMCP pre-renders the header band (title + progress bar) and purpose. You fill 6 sections:
✓ chose X → reason / ~ uncertain / ? risky guess⚠ If X → Y plain English sentences★ things found during exploration not in the plan◆ questions the user needs to answer+ gain │ − lose │ · skip→ investigate, weak spots, quick wins, plan gaps| Mistake | Fix |
|---|---|
| Rendering in a code block | Include the template directly in your response text |
| Restating the plan | Surface what ISN'T in the plan |
| Silent rendering | Discuss recommendations and questions with the user after |
| Verbose text | One short line per item, minimal words |