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/harrydaihaolin/splitwise-mcp/agents-mdgit clone --depth 1 https://github.com/harrydaihaolin/splitwise-mcpWhat 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 | $0.00693 | $0.00693 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
splitwise-mcp AGENTS.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 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in this repository.
What this is
splitwise-mcp is a Model Context Protocol
server that exposes the Splitwise API as MCP tools. Python, stdio transport,
personal-API-key auth.
Setup
Requires Python ≥ 3.10. Uses uv.
uv sync --extra dev # create venv + install runtime and dev deps
Test
uv run pytest # full suite (no network — uses httpx.MockTransport + a fake client)
uv run pytest -q tests/test_server.py # a single file
Tests must never hit the live Splitwise API. Mock at the httpx transport
layer (tests/test_client.py) or inject a fake client (tests/test_server.py).
Run
SPLITWISE_API_KEY=your_key python -m splitwise_mcp # serve over stdio
# or the console script:
SPLITWISE_API_KEY=your_key uv run splitwise-mcp
Get a key at https://secure.splitwise.com/apps. The key is read only from
the SPLITWISE_API_KEY environment variable — never hard-code or log it.
Layout
src/splitwise_mcp/
client.py # SplitwiseClient: auth, HTTP, error translation. One method per endpoint.
format.py # pure functions trimming verbose API JSON to compact dicts (saves tokens)
server.py # FastMCP instance, tool definitions, split math, main()
tests/ # test_client.py, test_format.py, test_server.py
docs/specs/ # design docs (source of truth for intent)
Design rules (follow these)
- Thin wrapper. Tools expose clean Splitwise operations; the calling
agent does the reasoning. Name→ID resolution (e.g. "Alex" → friend id) is
done by the agent calling
list_friends/list_groups, not by server-side fuzzy matching. Don't add hidden matching logic. - Trim responses. Every tool returns through a
format.pyfunction. When adding an endpoint, add a formatter — don't return raw Splitwise JSON. - Errors are readable.
client.pyraisesSplitwiseErrorwith a clear message (it also catches theerrors-in-a-200 quirk). Let it propagate from tools; FastMCP surfaces it to the agent. - Money is cent-accurate. Equal splits go through
server.equal_shares, which distributes leftover cents so owed shares sum exactly to cost. Reuse it; don't reinvent rounding. - Match the surrounding style. Small, focused modules; one clear purpose each. Keep files small enough to hold in context.
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 · 74 lines · 693 tokens per session scan A f44ab5dff9e8
splitwise-mcp AGENTS.md is an instructions file published in the GitHub repository harrydaihaolin/splitwise-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 693 tokens to every session, about $0.0035 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.