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/hyperdrift-io/deputy-workforce-mcp/agents-mdgit clone --depth 1 https://github.com/hyperdrift-io/deputy-workforce-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/hyperdrift-io/deputy-workforce-mcp/agents-md)<a href="https://agentmods.dev/instructions/hyperdrift-io/deputy-workforce-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hyperdrift-io/deputy-workforce-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 | $0.00451 | $0.00451 |
| Opus 5 | $0.00226 | $0.00226 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
deputy-workforce-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 5d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deputy Workforce Operations MCP
This repository is MCP Maker delivery mcp-maker-001-deputy. It inherits the Hyperdrift
workspace operating rules and exists to prove the MCP Maker proposition with useful foundations
built toward a production-ready delivery standard. Live Deputy integration remains pending
sandbox and customer workflow verification.
Mission alignment
Before changing the product, read MISSION.md. Preserve the approved experience pillars and do
not implement a rejected direction without founder approval.
Delivery rules
- Build a curated workforce-operations MCP, not a generic Deputy endpoint mirror.
- Keep every tool read-only. No Deputy mutation endpoint belongs in V1.
- Ground findings in source record identifiers, query periods, and explicit rules or thresholds.
- Do not score employees, infer protected characteristics, or present operational signals as payroll, employment, or legal advice.
- Do not emit names, emails, pay rates, free-text comments, or credentials in telemetry.
- Keep the deployment boundary single-tenant until paid demand justifies another model.
- Support local stdio and authenticated remote streamable HTTP from the same tool definitions.
- Use Node.js 22, strict TypeScript ESM, pnpm, and
.jsrelative import suffixes. - Shared transport and safety primitives come from
@hyperdrift-io/mcp-service-kit; provider contracts, workflows, configuration, and Deputy's stricter no-date telemetry stay in this repository. - Runtime dependencies are limited to
@modelcontextprotocol/sdk,@hyperdrift-io/mcp-service-kit, andzodunless the founder approves a change. - During prototype discovery, verify with install, type-check, build, security scan, Deputy sandbox exercises, and manual MCP protocol checks. Do not add automated product test suites until the direction is declared stable.
User-facing voice
Follow Hyperdrift's Speak to Enable covenant: strengths first, evidence second, next move third. Missing data limits confidence in the result; it is not a user failure.
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.
- 5d ago First seen · 41 lines · 451 tokens per session scan A 10123aa73f82
deputy-workforce-mcp AGENTS.md is an instructions file published in the GitHub repository hyperdrift-io/deputy-workforce-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 451 tokens to every session, about $0.0023 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
unity-mcp CLAUDE.md
Claude Code instructions for CoplayDev/unity-mcp, covering claude.md, what this project is, architecture, three layers on the python side and transport modes.
Unity-MCP copilot-instructions.md
Copilot instructions for IvanMurzak/Unity-MCP, covering project guidelines, critical rules, no c# reflection for private access, code review and code style.
Unity-MCP CLAUDE.md
Claude Code instructions for IvanMurzak/Unity-MCP, covering claude.md, what this is, build / run, project constitution and find detail in.
mcp-nixos copilot-instructions.md
Copilot instructions for utensils/mcp-nixos, covering github copilot instructions for mcp-nixos, project context, core development workflows, build & test commands (nix flake required) and testing strategy.
mcp-nixos CLAUDE.md
Claude Code instructions for utensils/mcp-nixos, a project described as: MCP-NixOS - Model Context Protocol Server for NixOS resources.
atlasclaw AGENTS.md
AGENTS.md instructions for CloudChef/atlasclaw, covering agents.md - atlasclaw coding guidelines, build / test / lint commands, backend (python), run the service and run all tests.