Borrowing it
Nothing to install: this file belongs to chrischall/splitwise-mcp. 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/chrischall/splitwise-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/chrischall/splitwise-mcpWrote 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/chrischall/splitwise-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/splitwise-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/splitwise-mcp/claude-md/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/instructions/chrischall/splitwise-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/splitwise-mcp/claude-md.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 | $0.04162 | $0.04162 |
| Opus 5.5 | $0.01665 | $0.01665 |
| Sonnet 5.5 | $0.00832 | $0.00832 |
| Haiku 4.5 | $0.00416 | $0.00416 |
Grade A, and why
splitwise-mcp 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 10d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
splitwise-mcp
MCP server for Splitwise. Wraps the Splitwise REST API (https://secure.splitwise.com/api/v3.0) and exposes 31 tools to Claude over stdio. Built on @chrischall/mcp-utils (runMcp, createApiClient, readEnvVar, textResult).
Commands
npm run build # tsc + esbuild bundle → dist/index.js + dist/bundle.js
npm test # tsc typecheck + vitest run
npm run test:watch # vitest watch
npm run test:coverage # tsc typecheck + vitest run --coverage (v8 reporter, no thresholds)
Run locally (requires built dist/):
SPLITWISE_API_KEY=xxx node dist/index.js
Tool naming
All tools are prefixed sw_ (e.g. sw_list_expenses, sw_create_expense).
Architecture
src/
index.ts # MCP server entry — calls runMcp() from @chrischall/mcp-utils
# with name/version/banner + the register*Tools array
client.ts # SplitwiseClient (createApiClient wrapper) + exported `client`
# singleton; reads SPLITWISE_API_KEY, 1× 2s retry, 30s timeout,
# 16 MiB response cap (receipts: 25 MiB per call)
tools/
user.ts # sw_get_current_user, sw_get_user, sw_update_user
groups.ts # sw_list_groups, sw_get_group, sw_create_group,
# sw_delete_group, sw_undelete_group,
# sw_add_user_to_group, sw_remove_user_from_group
friends.ts # sw_list_friends, sw_create_friend, sw_delete_friend
expenses.ts # sw_list_expenses, sw_get_expense, sw_create_expense,
# sw_update_expense, sw_attach_receipt, sw_delete_expense,
# sw_undelete_expense
_list.ts # sw_list_expenses' local filters, cursor scan (200/page,
# 1000-record budget), rows view, inline comments
_create.ts # create pre-flight: category by name (cached), category
# inference, duplicate scan, split:"equal" resolution
_split.ts # equalSplit (minor-unit arithmetic) + resolveMember
_expense-state.ts # deleted-expense pre-check, 403 explanation,
# post_state, undelete verification
uploads.ts # sw_get_upload_url — signed PUT on mcp-host's blob store
# (signing: blobStoreFromEnv from @chrischall/mcp-utils/export)
receipts.ts # sw_get_receipt — authenticated receipt download,
# inline bytes, and PDF text extraction
_receipt.ts # receipt UPLOAD for create/update/attach: loadReceipt (upload_id |
# sandboxed path | base64, magic-byte type check, 10 MiB cap),
# buildReceiptForm, verifyReceiptStored, releaseUpload
# (deletes a used upload_id after a successful write)
utilities.ts # sw_get_notifications, sw_get_categories, sw_get_currencies,
# sw_get_comments, sw_create_comment, sw_delete_comment
_confirm.ts # confirmWrite(): the gate for the group/friend/user writes
hints.ts # _meta.mint context-group hints (group `money`): moneyMeta(),
# withToolMeta() for the mcp-utils-registered writes/batch/confirm
_brief.ts # view:"brief" for the canonical reads (sw_list_friends = whats-due,
# sw_get_notifications = whats-new): lines in the untrusted envelope
batch.ts # sw_confirm (registerConfirmTool) + sw_batch (registerBatchTool),
# registered LAST — sw_batch lists the writes before it
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.
- 10d ago Changed · +2 lines · +308 tokens per session f5fddcd01f6e
- 11d ago Changed · +4 lines · +82 tokens per session ca46534b4670
- 27d ago Changed · +3 tokens per session 1bf99542b88c
- 28d ago Changed · +18 lines · +653 tokens per session 7ed187d98c0f
- 1mo ago Changed · +4 lines · +170 tokens per session 6421c8d59388
- 1mo ago Changed · +3 lines · +147 tokens per session f25d27a87892
- 1mo ago Changed · +1 lines · +48 tokens per session 9c43501570fa
- 1mo ago Changed · +13 tokens per session 559e6bb82351
- 1mo ago Changed · -8 tokens per session 2154e2701cb1
- 1mo ago First seen · 135 lines · 2,746 tokens per session scan A 4b09b50c2b98
splitwise-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/splitwise-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 4,162 tokens to every session, about $0.0166 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 2026-08-31.
splitwise-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| splitwise-mcp CLAUDE.mdchrischall/splitwise-mcp | Instructions file | 2 | 2d ago | MIT | A | 4,162 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |
| generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginners | Instructions file | 124k | today | MIT | A | 2,981 | Codex, OpenCode |