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/saperly/saperly-mcp/agents-mdgit clone --depth 1 https://github.com/Saperly/saperly-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/saperly/saperly-mcp/agents-md)<a href="https://agentmods.dev/instructions/saperly/saperly-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/saperly/saperly-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 | $0.02467 | $0.02467 |
| Opus 5 | $0.01234 | $0.01234 |
| Sonnet 5 | $0.00493 | $0.00493 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
saperly-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 4d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: @saperly/mcp
Patterns and pitfalls for AI agents (Claude Desktop, Claude Code, Cursor) using the Saperly MCP server. If you are an MCP client reading this autonomously, the tool names and patterns below are canonical — see the generated tool index at the end of this file for the full list.
1. What Saperly is
Saperly is the phone carrier for AI agents. One API call gives any agent a real phone number with TCPA compliance, consent capture, and an audit trail built in. Hosted mode runs the AI for you (Saperly handles speech-to-text, the LLM call, and text-to-speech). Webhook mode lets your backend decide responses turn by turn. Audio mode streams raw audio over a WebSocket if you need full control of the media plane.
2. Installation
For Claude Code:
claude mcp add saperly -- npx -y @saperly/mcp
export SAPERLY_API_KEY=sk_live_...
For Claude Desktop, add this entry to claude_desktop_config.json:
{
"mcpServers": {
"saperly": {
"command": "npx",
"args": ["-y", "@saperly/mcp"],
"env": { "SAPERLY_API_KEY": "sk_live_..." }
}
}
}
Transport is stdio. The server is a Node.js 18+ binary published as @saperly/mcp.
3. Authentication
Saperly uses a two-tier credential model. The MCP server reads exactly one credential from the environment at startup; pick the tier that matches the tools you plan to call.
| Credential | Prefix | What it does | Where to get it |
|---|---|---|---|
| API key | sk_test_… / sk_live_… |
Place calls, send SMS, manage lines, query usage. | Portal, or minted by a service key via POST /v1/keys. |
| Service key | sk_svc_test_… / sk_svc_live_… |
Mint, list, get, update, rotate, revoke child API keys. Credential management only. | Portal only (Settings → Service Keys). |
Child API keys minted by a service key carry their own scope. The API accepts exactly four permission tiers on POST /v1/keys and PATCH /v1/keys/{id}. A fifth value, legacy_full, appears on responses for keys minted before v0.5.7.0 but cannot be set via the API.
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.
- 4d ago First seen · 169 lines · 2,467 tokens per session scan A 01f0ca30797a
saperly-mcp AGENTS.md is an instructions file published in the GitHub repository Saperly/saperly-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 2,467 tokens to every session, about $0.0123 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.