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/legacybridge-tech/claude-plugins/memory-remembernpx skills add legacybridge-tech/claude-plugins --skill memory-remembergit clone --depth 1 https://github.com/legacybridge-tech/claude-pluginsWhat 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 | $0.00042 | $0.00581 |
| Opus 5 | $0.00021 | $0.00291 |
| Sonnet 5 | $0.00008 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
memory-remember 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Remember
Store information into the appropriate memory file.
When to Use
Trigger proactively — do not wait for the user to ask — when:
- A new user preference or decision is discovered during conversation
- A milestone, architecture decision, or lesson learned is identified
- The conversation reaches a natural summary point or is ending
- The user explicitly asks to remember something
Workflow
1. Read Configuration
Read .claude/memory-settings.json to get the configured file names.
2. Get Current Timestamp
Before writing, run date '+%Y-%m-%d %H:%M' via Bash to get the current timestamp. Use this for any dated entry. Use date '+%Y-%m-%d' when only a date is needed.
3. Classify Content
Determine which file the memory belongs to:
| Type | Target File | Examples |
|---|---|---|
| Preference | preferences file | User likes, dislikes, habits, settings, personal info, project conventions |
| Conversation Summary | conversations file | What was discussed, tasks completed, decisions made in this session |
| Long-Term Memory | longterm file | Life events, milestones, architecture decisions, lessons learned, relationship changes |
4. Write to Appropriate File
Preferences File
- Read the current file
- Find the appropriate section for the new information
- Edit the existing section content (update, don't duplicate)
- Update the
Last Updated: {DATE}header to today's date
Conversations File
- Prepend new entry to the TOP of the file (below the header, above existing entries)
- Format:
### YYYY-MM-DD HH:MM - Topic(use the timestamp from step 2) - Include: brief summary of what was discussed, key decisions, action items
- Keep summaries concise (3-8 lines)
Long-Term Memory File
- Append to the appropriate section within the file
- Format:
- YYYY-MM-DD: Description(use date from step 2) - NEVER delete existing entries — only add new ones
- Place under the correct subsection (Milestones, Decisions, Lessons Learned, etc.)
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 · 67 lines · 42 tokens per session scan A 9ed244dac6a7
memory-remember is a skill published in the GitHub repository legacybridge-tech/claude-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 581 once invoked, about $0.0002 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…