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/webrenew/memories/memories-devnpx skills add webrenew/memories --skill memories-devgit clone --depth 1 https://github.com/webrenew/memoriesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/webrenew/memories/memories-dev)<a href="https://agentmods.dev/skills/webrenew/memories/memories-dev"><img src="https://agentmods.dev/badge/skills/webrenew/memories/memories-dev.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00117 | $0.01813 |
| Opus 5 | $0.00059 | $0.00907 |
| Sonnet 5 | $0.00023 | $0.00363 |
| Haiku 4.5 | $0.00012 | $0.00181 |
Grade A, and why
memories-dev 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 3d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memories-dev
Developer guide for contributing to the memories.sh monorepo.
Project Structure
memories/
├── packages/
│ ├── cli/ # @memories.sh/cli (npm package)
│ │ ├── src/
│ │ │ ├── commands/ # CLI commands (Commander.js)
│ │ │ ├── lib/ # Core: db, memory, auth, embeddings, git
│ │ │ └── mcp/ # MCP server (stdio + HTTP)
│ │ ├── tsup.config.ts # Build config
│ │ └── package.json
│ └── web/ # Next.js marketing + dashboard
│ ├── src/app/ # App Router pages + API routes
│ ├── src/components/ # UI components (shadcn/ui)
│ ├── src/lib/ # Auth, Stripe, Supabase, Turso
│ └── content/docs/ # Fumadocs documentation
├── supabase/ # Database migrations
├── skills/ # Distributable skills (this directory)
└── pnpm-workspace.yaml
Architecture Overview
Dependency Graph
db.ts (SQLite/libSQL, migrations, FTS5)
↓
memory.ts (CRUD, context, lifecycle sessions, compaction, consolidation, streaming)
↑ ↑ ↑
openclaw-memory.ts reminders.ts embeddings.ts (Xenova/Transformers, cosine similarity)
↑ ↑
git.ts openclaw.ts command bridge
↓
Commands ← auth.ts, turso.ts, config.ts, setup.ts
↓
MCP Server (stdio + StreamableHTTP transports)
↳ registerCoreTools (core + lifecycle + consolidation + reminders)
↳ registerStreamingTools (SSE chunk pipelines)
Key Lib Files
| File | Purpose |
|---|---|
db.ts |
SQLite via libSQL. Schema migrations, FTS5 triggers, getDb() singleton |
memory.ts |
Memory operations: add/search/list/forget/update, getContext, sessions, compaction checkpoints, consolidation, streaming |
openclaw-memory.ts |
OpenClaw file-mode contract (memory.md, daily logs, snapshots), workspace path resolution, read/write helpers |
embeddings.ts |
Local embeddings via Xenova/Transformers. generateEmbedding(), cosine similarity |
git.ts |
getProjectId() — derives project ID from git remote URL |
auth.ts |
Cloud auth token storage, device code flow helpers |
turso.ts |
Turso embedded replica sync (cloud ↔ local) |
config.ts |
YAML config read/write (~/.config/memories/) |
setup.ts |
Tool detection (Cursor, Claude, Windsurf, VS Code), MCP config setup |
templates.ts |
Built-in memory templates (decision, error-fix, api-endpoint, etc.) |
ui.ts |
Terminal styling: chalk, figlet, gradient, boxen |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 189 lines · 117 tokens per session scan A 4caa63441b61
memories-dev is a skill published in the GitHub repository webrenew/memories (36 stars, last pushed 9d ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,813 once invoked, about $0.0006 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 2026-08-30.
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…