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 instructions/makz81/spendlog/claude-mdgit clone --depth 1 https://github.com/makz81/spendlogWrote 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/instructions/makz81/spendlog/claude-md)<a href="https://agentmods.dev/instructions/makz81/spendlog/claude-md"><img src="https://agentmods.dev/badge/instructions/makz81/spendlog/claude-md.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 | $0.00663 | $0.00663 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
spendlog CLAUDE.md 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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spendlog
MCP server for expense tracking. Track finances directly in Claude.
Tech Stack
| Layer | Technology |
|---|---|
| Runtime | Node.js 20+ (ESM, TypeScript strict) |
| MCP | @modelcontextprotocol/sdk |
| Database | TypeORM + better-sqlite3 (SQLite) |
| Validation | Zod |
| Testing | Vitest (382 tests) |
| i18n | EN (default), DE |
Commands
npm run dev # MCP server with watch mode (tsx)
npm run build # TypeScript build
npm run start # Run built server
npm run test # Run tests
npm run typecheck # Type check (no emit)
npm run db:migrate # Run database migrations
npm run db:seed # Seed default categories
npm run db:reset # Reset DB (delete + migrate + seed)
Architecture
User -> Claude LLM -> MCP Tool Call -> Zod Validation -> Service -> TypeORM -> SQLite
Data Flow
- MCP tools receive params via stdio (Claude Desktop) or HTTP/SSE (cloud)
- Zod validates all inputs
- Services contain business logic
- TypeORM entities map to SQLite tables in
~/.spendlog/spendlog.db
Key Directories
src/
index.ts # MCP server entry point
server.ts # Server setup & tool registration
cli.ts # CLI installer (npx spendlog)
constants.ts # App constants
tools/ # MCP tool definitions (one file per tool group)
entities/ # TypeORM entities (Transaction, Invoice, etc.)
services/ # Business logic (pdf, sync, connection)
db/ # Database setup, migrations, seeds
i18n/ # Translation dictionaries
templates/
invoice.hbs # Handlebars template for PDF invoices
tests/
tools/ # Integration tests per tool group
helpers/ # Test utilities
fixtures/ # Test data factories
Code Conventions
- TypeScript strict -- no
anywithout comment - MCP Tools: snake_case names, Zod schemas, English descriptions (localized via i18n)
- Services: camelCase functions, throw errors (handled in tool layer)
- Entities: PascalCase, TypeORM decorators, UUID primary keys
- Files: kebab-case (
transaction-service.ts) - Imports: external -> internal -> relative, no circular deps
- ESM:
import/export, notrequire
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.
- 4d ago First seen · 80 lines · 663 tokens per session scan A c921ae042d17
spendlog CLAUDE.md is an instructions file published in the GitHub repository makz81/spendlog (1 stars, last pushed 2mo ago), licensed MIT. It adds 663 tokens to every session, about $0.0033 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 instructions, from other repositories
rekal AGENTS.md
Instructions for janbjorge/rekal, covering rekal: agent instructions, what this project is, architecture, key rules and re-expansion bar.
Vault-Agent-Memory AGENTS.md
Instructions for zycaskevin/Vault-Agent-Memory, covering agent instructions for vault agent memory, common install architecture, second decision: optional features, first decision: database scope and safe agent workflow.
rekal CLAUDE.md
Instructions for janbjorge/rekal, a project described as: Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.
zen CLAUDE.md
Claude Code instructions for sheshbabu/zen, covering claude.md, development commands, build commands, dependencies and go build tags.
db-mcp copilot-instructions.md
Copilot instructions for neverinfamous/db-mcp, covering db-mcp — copilot code review context, project overview, session context, coding standards and naming.
state-memory-mcp copilot-instructions.md
Instructions for putervision/state-memory-mcp, covering state memory (state-memory-mcp), 1. priority order, 2. when to write to the graph, 3. workflow pattern and 4. codebase seeding on initialization.