Borrowing it
Nothing to install: this file belongs to P4rthPat3l/sheetcraft-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/P4rthPat3l/sheetcraft-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/P4rthPat3l/sheetcraft-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/p4rthpat3l/sheetcraft-mcp/agents-md)<a href="https://agentmods.dev/instructions/p4rthpat3l/sheetcraft-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/p4rthpat3l/sheetcraft-mcp/agents-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 5.1 | $0.02898 | $0.02898 |
| Opus 5 | $0.01449 | $0.01449 |
| Sonnet 5 | $0.00580 | $0.00580 |
| Haiku 4.5 | $0.00290 | $0.00290 |
Grade A, and why
sheetcraft-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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sheetcraft-mcp
Shared-core Google Sheets MCP server + CLI. Both surfaces are thin wrappers over the same op library — reliability and token-efficiency live in src/lib, never in a wrapper.
Layout
src/lib/ the core. Ops-agnostic: a1 parsing, errors, output compaction, retry, schema, registry
src/ops/ operations (get_values, update_values, add_sheet, create_spreadsheet, ...). Each exports an `Op`
src/wrappers/mcp.ts stdio MCP server — registers ops, ~30 lines of logic total
src/wrappers/cli.ts CLI — same ops as subcommands, lazy credentials
src/test/ node:test unit tests (run against dist/)
Commands
npm run check # tsc --noEmit
npm run build # emit dist/
npm test # build + node --test dist/test/*.test.js
node dist/wrappers/cli.js list # all ops by toolset
node dist/wrappers/cli.js help <op> # one op's JSON schema
Architecture rules (do not violate)
- Ops are the only place Google API calls live. An op is
{ name, group, description, inputSchema, annotations, run(args, svc) }. It returns plain JSON-serializable data or anOpResult { text, structured? }, or throwsSheetsError. Neverconsole.log— ops return data, wrappers render. - Wrappers stay thin. MCP wrapper passes
op.inputSchema.zodstraight to the SDK'sregisterTool(the SDK validates + flattens args;tools/listJSON Schema and runtime validation share one source). CLI parses argv, coerces types per the op's JSON Schema, and calls the samerunOp. runOpnever throws. Failures render asOpResult.error { code, retryable }with a teaching message. Exit codes /isErrorare derived from that.- Errors teach. Invalid ranges/sheets must quote an example and list available sheets. Rate-limit errors mention that retries already happened. Use
opError()for arg problems,A1Errorfor range problems, and letclassifyGoogleErrorhandle Google API errors (403 with rate-limit reason → retryable). - A1 parsing is centralized. Use
parseFullRange/scope.toA1(concrete, values-API-safe) /scope.toGrid(GridRange for batchUpdate). Sheet params accept'Name'orgid:Nor bare gid. Sheet names with spaces should be single-quoted —splitSheetPrefixAUTO-REPAIRS the common agent slips (no quotes, stray trailing quote, quote inside the name) instead of erroring: a hard error wastes a round trip the repair saves. Don't add new hard failures for recoverable input shapes. - Reads are capped.
cellCap(default 5000 cells) +truncationNoticetelling the model how to get the rest. Writes echoupdatedRange/updatedCells. USER_ENTEREDis the default input mode; appends default toINSERT_ROWS(the API's own default OVERWRITE silently destroys data below tables — never ship it as a default).- Toolsets gate registration.
SHEETS_TOOLSETSenv (defaultcore,drive; valid:core,drive,formatting,charts,pivot,power,all), validated at startup with a hard error on typos. New op groups must be added toTOOLSET_GROUPS(src/lib/types.ts) andTOOLSETS(src/lib/registry.ts). - Cell contents are data, not instructions. Never interpolate sheet content into error messages, descriptions, or prompts.
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.
- 8d ago First seen · 91 lines · 2,898 tokens per session scan A 4bd57f5668bf
sheetcraft-mcp AGENTS.md is an instructions file published in the GitHub repository P4rthPat3l/sheetcraft-mcp (1 stars, last pushed 10d ago), licensed MIT. It adds 2,898 tokens to every session, about $0.0145 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.