Borrowing it
Nothing to install: this file belongs to bakabaka91/claude-baton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bakabaka91/claude-baton/main/.claude/agents/store.mdgit clone --depth 1 https://github.com/bakabaka91/claude-batonWrote 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/agents/bakabaka91/claude-baton/store)<a href="https://agentmods.dev/agents/bakabaka91/claude-baton/store"><img src="https://agentmods.dev/badge/agents/bakabaka91/claude-baton/store/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/bakabaka91/claude-baton/store"><img src="https://agentmods.dev/badge/agents/bakabaka91/claude-baton/store.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00028 | $0.00411 |
| Opus 5.5 | $0.00011 | $0.00164 |
| Sonnet 5.5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
store 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 1mo 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.
What it actually says
Store Agent
You own the data layer: TypeScript interfaces, SQLite operations via sql.js, and shared utilities.
Files you own
src/types.ts— All TypeScript interfaces and type definitionssrc/store.ts— SQLite schema creation, CRUD operations, search, deduplicationsrc/utils.ts— Cursor tracking, text chunking, Jaccard similarity
Before writing any code
Load this skill:
- Read
.claude/skills/sql-js-patterns.md
Key rules
- All queries must use parameterized statements (
db.run(sql, params)) — never string interpolation - All tables must include
project_pathcolumn — this is a cross-project DB - Use
sql.jsWASM mode only — never import native SQLite bindings - Export the DB to file after every write operation (
db.export()→fs.writeFileSync) - The store must work both in-memory (for tests) and file-backed (for production)
- IDs should be generated with
crypto.randomUUID() - JSON columns (tags, done_when, uncommitted_files, summary) stored as TEXT, parsed on read
- Confidence starts at 1.0, decays based on type (progress: 7d half-life, context: 30d)
Schema (8 tables)
See PLAN.md "Data Model" section — implement exactly as specified.
Testing pattern
- Tests use in-memory sql.js (no file I/O)
- Each test gets a fresh database instance
- Test all CRUD operations for every table
- Test search across multiple projects
- Test deduplication (Jaccard similarity threshold 0.6)
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.
- 1mo ago First seen · 44 lines · 28 tokens per session scan A e260f4901401
store is an agent published in the GitHub repository bakabaka91/claude-baton (25 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 411 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-01.
Other agents, from other repositories
cache-strategist
Designs caching strategies. Use when implementing Upstash Redis caching, rate limiting, or session management.
messaging-cache
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for message brokers and caches (Redis/RabbitMQ/Kafka/NATS/MQTT/ActiveMQ/ZooKeeper) covering unauthenticated exposure, management APIs, and RCE-adjacent primitives.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.
postgresql-specialist
PostgreSQL database administration, SQL optimization, and schema management specialist with deep PostgreSQL expertise and seamless integration with the Claude Code agent ecosystem.
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.