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/sinch/skills/claude-mdgit clone --depth 1 https://github.com/sinch/skillsWrote 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/sinch/skills/claude-md)<a href="https://agentmods.dev/instructions/sinch/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/sinch/skills/claude-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 | $0.00912 | $0.00912 |
| Opus 5 | $0.00456 | $0.00456 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
skills CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Use curl and Node.js SDK (`@sinch/sdk-core`) for code examples. Exception: Mailgun skills use `mailgun.js`. How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Purpose
Official Sinch API skills for AI coding agents. Each skill in skills/ provides getting-started guides, best practices, and gotchas for a Sinch product. Skills are installed by developers via npx skills add sinch/skills and are listed on https://skills.sh/.
Architecture
skills/
<product>/
SKILL.md # Main skill file (required)
scripts/ # Optional helper scripts
references/ # Optional detailed reference material
assets/ # Optional images or other assets
One folder per Sinch product. The skill file is always SKILL.md.
Adding a New Skill
- Create
skills/<product-name>/SKILL.mdwith YAML frontmatter (---delimiters,nameanddescriptionfields) - Fill in the YAML frontmatter (
nameinsinch-<product>format,descriptionwith what it does and when to use it) - Complete all body sections: Overview, Getting Started, Key Concepts, Common Patterns, Gotchas & Best Practices, Links
- Keep the file under 500 lines. Move detailed content to
references/if needed.
SKILL.md Format Rules
Frontmatter
name: Max 64 characters. Format:sinch-<product-slug>(e.g.,sinch-sms,sinch-voice-api)description: Max 1024 characters. Describes when to trigger the skill (e.g., "When the user wants to send SMS messages using the Sinch SMS API")
Body Sections
- Overview -- What the product does and when to use it (2-3 sentences)
- Getting Started -- Authentication, SDK install, first API call
- Key Concepts -- Product-specific domain model and terminology
- Common Patterns -- Most frequent use cases with code snippets
- Gotchas and Best Practices -- Non-obvious pitfalls, rate limits, regional quirks
- Links -- Documentation, API reference, dashboard
Style Guidelines
- Max 500 lines per SKILL.md; move detailed content to
references/ - Write for AI agents: concise, actionable, include code examples
- Use curl and Node.js SDK (
@sinch/sdk-core) for code examples. Exception: Mailgun skills usemailgun.js. - Do not include lengthy prose; prefer bullet points and code blocks
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 · 83 lines · 912 tokens per session scan A 9dac51a23142
skills CLAUDE.md is an instructions file published in the GitHub repository sinch/skills (9 stars, last pushed 8d ago), licensed Apache-2.0. It adds 912 tokens to every session, about $0.0046 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
toh-framework CLAUDE.md
Claude Code instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
claude-code-templates CLAUDE.md
Claude Code instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
bdb-dev-optimized-agent-skills CLAUDE.md
Claude Code instructions for hybridlabor-api/bdb-dev-optimized-agent-skills, covering bdb agent skills — global instructions, docs & pipeline, how many agents, safety gate — mechanically enforced, not advisory and non-negotiable.