agentmods.dev

skills: Instructions file for Claude Code

CLAUDE.md

skills CLAUDE.md is an instructions file for Claude Code from sinch/skills. It costs 921 tokens per session, scanned A, original, Apache-2.0.

A repository-specific guide for official Sinch API skills, which help AI coding agents work with Sinch communication products. It defines the folder layout and the required sections for each product guide.

In plain words
What is it for?
Use it when creating or updating a Sinch product skill, including its main guide, helper scripts, reference material, assets, and product-specific configuration.
Why use it?
It provides a consistent way to document setup, common usage, limitations, and links for each Sinch product. This prevents new skills from missing required files or useful guidance.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is sinch/skills's own configuration. It tells Claude Code how to work on skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills configures →

not rated 11repo changed 1mo ago A scan 921 tokens original Apache-2.0
View source ↗ sinch/skills sinch.com
Reuse

Borrowing it

Nothing to install: this file belongs to sinch/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sinch/skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sinch/skills

Made for: Claude Code.

Wrote 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.

agentmods badge for skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sinch/skills/claude-md/github.svg)](https://agentmods.dev/instructions/sinch/skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sinch/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/sinch/skills/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sinch/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/sinch/skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 921 This file is loaded in full into every session.
When invoked 921 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00921 $0.00921
Opus 5.5 $0.00368 $0.00368
Sonnet 5.5 $0.00184 $0.00184
Haiku 4.5 $0.00092 $0.00092

Measured 1mo ago against content hash 5522345ea2a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skills CLAUDE.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 1mo 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.

CLAUDE.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 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 using the Sinch skills in this repository to build against Sinch APIs. The full usage guide, including the task-to-skill routing table, is AGENTS.md. To create or edit skills, follow CONTRIBUTING.md.

Repository Purpose

Official Sinch API skills for AI coding agents. Each skills/<product>/SKILL.md is a self-contained brief for one Sinch product: authentication, first API call, domain model, common patterns, gotchas, and links to the canonical documentation. Skills are installed via npx skills add sinch/skills and are listed on https://skills.sh/.

Working With a Skill

  1. Pick the product skill whose description matches the request. Use the routing table in AGENTS.md. Load the smallest set of skills that owns the behavior; the product skill says which supporting skills to load and when.
  2. Read the skill's Agent Instructions section before writing code. It holds the binding policy digest, what to infer versus ask, and which other skills to load.
  3. Read references/shared-policy.md once per conversation. Skip further copies with the same ID, version, and fingerprint.
  4. Check the Overview for version scope. For example, sinch-voice-api covers Voice API v1 only; the preview Voice API v2 is covered by sinch-voice-api-v2.
  5. Follow Getting Started and Common Patterns for the implementation, and Gotchas and Security before finishing.

Rules That Change What You Do

  • Fetch before you state. Endpoint paths, methods, field names, enums, limits, webhook payloads, and SDK signatures must come from the canonical document fetched in the current session, linked from the skill's Links section. Bundled references/, scripts/, and examples are illustrations, never schema authority.
  • Never guess a docs URL. If a fetch fails, re-search already fetched documents, consult https://developers.sinch.com/llms.txt, follow first-party links, retry once, then stop and say so.
  • Approval to write code is not approval to run it. Classify each operation as read-only, reversible, billable, or destructive. Ask before billable or destructive calls such as sending messages, placing calls, or renting numbers.
  • Bound every loop. Polling and retries need backoff, jitter, and a hard cap. Report a timeout as unknown, not as failure.
  • Report verification levels separately. Lint, unit, mock contract, sandbox, live, end-to-end. Say which you did not run. An HTTP 2xx does not prove delivery.
  • If a required skill is missing, name it and stop rather than improvising its content.

Read the full file on GitHub · 44 lines

Changes

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.

  1. 1mo ago Changed · -10 tokens per session 5522345ea2a1
  2. 1mo ago Changed · -39 lines · +19 tokens per session ffc4ae84cbc4
  3. 2mo ago First seen · 83 lines · 912 tokens per session scan A 9dac51a23142

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository sinch/skills (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 921 tokens to every session, about $0.0037 per session on Opus 5.5. 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.

aeoagentic-aiagentic-workflowaiai-agentai-agents
Related

skills CLAUDE.md compared with instructions from other repositories

skills CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skills CLAUDE.mdsinch/skillsInstructions file111mo agoApache-2.0A921Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode