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/vectojs/numera-mcp/agents-mdgit clone --depth 1 https://github.com/vectojs/numera-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/vectojs/numera-mcp/agents-md)<a href="https://agentmods.dev/instructions/vectojs/numera-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vectojs/numera-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 | $0.00212 | $0.00212 |
| Opus 5 | $0.00106 | $0.00106 |
| Sonnet 5 | $0.00042 | $0.00042 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
numera-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 3d 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
Numera MCP Agent Guide
This repository owns only the stdio Model Context Protocol adapter and its safe filesystem boundary. Workbook semantics remain in exact-pinned Numera Core and XLSX packages.
- Keep stdout protocol-only. Diagnostics belong on stderr.
- Keep all file access beneath the configured
--root; reject traversal, absolute paths, NUL bytes, and symlink escapes. - Mutation tools preserve inputs, require a fresh output path and expected SHA-256, validate the complete batch before writing, and commit atomically.
- Tool schemas expose intention-level workbook operations, never browser, Canvas, VectoJS Scene, or CLI subprocess concepts.
- Write documentation and code comments in English. Comments explain security invariants, ownership, and non-obvious tradeoffs.
- Use Bun, TypeScript 7, Oxlint, Prettier, Changesets, and the repository's
verification scripts. Follow the workspace root
AGENTS.mdfor workstreams, releases, governance, and documentation.
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.
- 3d ago First seen · 19 lines · 212 tokens per session scan A 424d20add606
numera-mcp AGENTS.md is an instructions file published in the GitHub repository vectojs/numera-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 212 tokens to every session, about $0.0011 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
fcp-sheets CLAUDE.md
Instructions for os-tack/fcp-sheets, covering fcp-sheets, project overview, architecture, key patterns and commands.
gno CLAUDE.md
Claude Code instructions for gmickel/gno, a project described as: Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST API and MCP support for AI clients.
docgen-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/docgen-mcp-server, covering developer protocol, what this server does, core rules, patterns and tool.
docgen-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/docgen-mcp-server, covering developer protocol, what this server does, core rules, patterns and tool.
excel-mcp CLAUDE.md
Claude Code instructions for ASH1998/excel-mcp, covering claude.md, project overview, architecture, current implementation status and ✅ completed: file operations (phase 1).
mcp-server-excel copilot-instructions.md
Copilot instructions for sbroenne/mcp-server-excel, covering github copilot instructions - excelmcp, repository map, environment, working rules and build and validation.