Conversation
📝 WalkthroughWalkthroughDocumentation updates standardize CLI flags (--title/-t, --importance/-i), expand memory category taxonomy (fact, procedure, experience), and remove source-thread references. A new plugin update workflow section is added to the README. No functional code modifications. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. 📜 Recent review detailsConfiguration used: defaults Review profile: CHILL Plan: Pro 📒 Files selected for processing (5)
🧰 Additional context used📓 Path-based instructions (1)examples/**/AGENTS.md📄 CodeRabbit inference engine (examples/AGENTS.md)
Files:
🧠 Learnings (4)📚 Learning: 2026-01-08T09:26:48.387ZApplied to files:
📚 Learning: 2026-01-08T09:26:48.387ZApplied to files:
📚 Learning: 2026-01-08T09:26:48.387ZApplied to files:
📚 Learning: 2026-01-08T09:26:48.387ZApplied to files:
🔇 Additional comments (9)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
nowledge-mem-codex-prompts/distill.md (1)
33-49: Update flag format to match SKILL.md and standardize across PR.This file still uses long flags (--title, --importance) while the related SKILL.md file was updated to use short flags (-t, -i). To complete the PR's standardization objective, update all examples in this file to use the short flag format.
♻️ Suggested update
-nmem m add "Bullet list or short paragraph capturing the key insight" \ - --title "Brief, searchable title" \ - --importance 0.8 +nmem m add "Bullet list or short paragraph capturing the key insight" \ + -t "Brief, searchable title" \ + -i 0.8Apply the same changes to the example on lines 41-43 and the programmatic use example on line 49.
nowledge-mem-claude-code-plugin/README.md (1)
252-253: Update Distill Memory example to use short flags for consistency.The code example on line 252 still references long flags
--titleand--importance. To align with the broader PR changes (SKILL.md now uses-tand-i), update this to use short flags.♻️ Suggested update
-3. If approved, runs `nmem m add "<content>" --title "<title>" --importance <score>` +3. If approved, runs `nmem m add "<content>" -t "<title>" -i <score>`
📜 Review details
Configuration used: defaults
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (5)
examples/AGENTS.mdnowledge-mem-claude-code-plugin/README.mdnowledge-mem-claude-code-plugin/commands/sum.mdnowledge-mem-claude-code-plugin/skills/distill-memory/SKILL.mdnowledge-mem-codex-prompts/distill.md
🧰 Additional context used
📓 Path-based instructions (1)
examples/**/AGENTS.md
📄 CodeRabbit inference engine (examples/AGENTS.md)
Add Nowledge Mem Integration section to project's
AGENTS.mdfile to enable AI agents to autonomously manage knowledge
Files:
examples/AGENTS.md
🧠 Learnings (4)
📚 Learning: 2026-01-08T09:26:48.387Z
Learnt from: CR
Repo: nowledge-co/community PR: 0
File: examples/AGENTS.md:0-0
Timestamp: 2026-01-08T09:26:48.387Z
Learning: Applies to examples/.claude/agents/memory-keeper.md : For Claude Code users, create a memory-keeper agent at `.claude/agents/memory-keeper.md` that proactively saves insights, decisions, and learnings to Nowledge Mem after completing tasks
Applied to files:
nowledge-mem-claude-code-plugin/skills/distill-memory/SKILL.mdnowledge-mem-claude-code-plugin/commands/sum.mdnowledge-mem-codex-prompts/distill.mdexamples/AGENTS.md
📚 Learning: 2026-01-08T09:26:48.387Z
Learnt from: CR
Repo: nowledge-co/community PR: 0
File: examples/AGENTS.md:0-0
Timestamp: 2026-01-08T09:26:48.387Z
Learning: Applies to examples/**/AGENTS.md : Add Nowledge Mem Integration section to project's `AGENTS.md` file to enable AI agents to autonomously manage knowledge
Applied to files:
nowledge-mem-claude-code-plugin/skills/distill-memory/SKILL.mdexamples/AGENTS.md
📚 Learning: 2026-01-08T09:26:48.387Z
Learnt from: CR
Repo: nowledge-co/community PR: 0
File: examples/AGENTS.md:0-0
Timestamp: 2026-01-08T09:26:48.387Z
Learning: Use importance scale 0.8-1.0 for critical decisions, breakthroughs, and blockers resolved; 0.5-0.7 for useful insights and standard decisions; 0.1-0.4 for background info and minor details when setting memory importance in Nowledge Mem
Applied to files:
nowledge-mem-claude-code-plugin/skills/distill-memory/SKILL.mdnowledge-mem-claude-code-plugin/commands/sum.mdexamples/AGENTS.md
📚 Learning: 2026-01-08T09:26:48.387Z
Learnt from: CR
Repo: nowledge-co/community PR: 0
File: examples/AGENTS.md:0-0
Timestamp: 2026-01-08T09:26:48.387Z
Learning: Use memory categories (insight, decision, fact, procedure, experience) as labels when creating memories in Nowledge Mem
Applied to files:
nowledge-mem-claude-code-plugin/skills/distill-memory/SKILL.mdnowledge-mem-claude-code-plugin/commands/sum.mdnowledge-mem-codex-prompts/distill.mdexamples/AGENTS.md
🔇 Additional comments (9)
nowledge-mem-claude-code-plugin/skills/distill-memory/SKILL.md (2)
36-39: Verify CLI flag format consistency across documentation files.The official Nowledge Mem CLI documentation shows
nmem m add "Important insight" --title "Project Learnings"using long flags. However, this file uses short flags (-t, -i) while distill.md continues to use long flags (--title, --importance). Ensure the current nmem CLI version supports both formats, or standardize across all documentation files.
51-59: LGTM — Examples align with skill purpose.Both examples (React hooks cleanup and PostgreSQL decision) effectively demonstrate high-value insights worth preserving, with appropriate importance scores and clear, actionable content.
nowledge-mem-claude-code-plugin/README.md (1)
129-141: Verify plugin update command syntax.The new "Update Plugin" section is well-structured and helpful. However, verify that the command
claude plugin update nowledge-mem@nowledge-communityuses the correct plugin identifier and syntax for the current version of Claude Code.examples/AGENTS.md (3)
1-13: Nowledge Mem Integration section successfully implements guideline requirements.The section provides comprehensive guidance for AI agents to autonomously manage knowledge through structured memory operations. Memory categories are clearly defined, establishing the taxonomy specified in the learnings (insight, decision, fact, procedure, experience), and the phrasing "Use these categories to guide content structure" effectively guides content organization.
15-27: Memory creation examples correctly standardize to short flags.Both examples demonstrate the updated CLI interface (-t for title, -i for importance) consistently. The progression from basic to titled/importance-tagged memory is instructive and aligns with the current nmem CLI version.
57-89: Memory Keeper Agent provides practical autonomous memory workflow.The agent definition correctly categorizes memories (line 78) and uses the updated CLI syntax in the example (lines 84-85 with -t and -i flags). The agent is positioned to enable proactive knowledge capture aligned with the category taxonomy.
nowledge-mem-claude-code-plugin/commands/sum.md (3)
9-17: Memory Categories definition is consistent with examples/AGENTS.md.The taxonomy and phrasing match across both files, providing unified documentation for the expanded category system (fact, procedure, experience added alongside existing insight, decision). The descriptions are clear and actionable.
24-30: Command documentation correctly reflects updated CLI interface.The example demonstrates the standardized short flags (-t and -i) and includes the 60-character title limit constraint, providing users with practical usage guidance aligned with the current nmem CLI version.
45-51: Example demonstrates high-quality memory with proper importance scaling.The React useEffect example is atomic, actionable, and standalone—meeting the Quality Standards (lines 38-43). The importance level 0.9 correctly reflects this as a critical pattern that prevents bugs, consistent with the 0.8-1.0 range guidance from learnings.
1 participant
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.