Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/danielrosehill/claude-user-memory-plugin/commit-learningsnpx skills add danielrosehill/Claude-User-Memory-Plugin --skill commit-learningsgit clone --depth 1 https://github.com/danielrosehill/Claude-User-Memory-PluginWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00108 | $0.00839 |
| Opus 5 | $0.00054 | $0.00419 |
| Sonnet 5 | $0.00022 | $0.00168 |
| Haiku 4.5 | $0.00011 | $0.00084 |
Grade A, and why
commit-learnings scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit end-of-session learnings
Over a long session, facts accumulate that weren't important enough to trigger remember-user-fact in the moment but, in aggregate, amount to a meaningful update to what memory knows about the user. This skill is the sweep — a structured review before the session ends.
When to invoke
- User says "save what you learned", "commit this to memory", "update memory", or similar.
- User is wrapping up a session (handover,
/clear, end-of-day). - Proactively, when a long session has clearly surfaced durable facts you haven't saved yet.
- Before a handover document is written — the next session should inherit the learnings.
Do not invoke:
- In short sessions where nothing new was learned about the user.
- When the only "learnings" are transient task state (what got done this session belongs in a handover doc, not memory).
How to run it
1. Load the config
Read .claude/memory-config.md in the workspace. You will need the backend's search tool (for the duplicate check) and add/update tool (for the writes), plus scope parameters for both personal and work contexts. If the file is missing, stop and ask the user to install one.
2. Scan the session
Walk back through the conversation and list every candidate fact. For each, ask:
- Is it about the user (preferences, role, context, corrections) rather than the code or task?
- Is it durable — still true next week, next month?
- Is it not already in memory? Quickly search to check.
- Is it not sensitive (no credentials, tokens, private third-party info)?
A fact that passes all four is a commit candidate.
3. Group by context
Separate candidates into personal and work piles using the deduction rule in CONTEXT.md. A single session can produce commits to both stores — that's fine, just keep them separate.
4. Show the user before saving
This skill is different from remember-user-fact because it's batch and retrospective — the user may not remember telling you half of this. Before saving, show the proposed commits:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 75 lines · 108 tokens per session scan A 2aa8b86f7f7c
commit-learnings is a skill published in the GitHub repository danielrosehill/Claude-User-Memory-Plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 108 tokens to every session and 839 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…