stack-anthropic-claude

stack-anthropic-claude is a skill for Claude Code from e-t-y-b/etyb-skills. It costs 301 tokens per session (4,242 once invoked), scanned A, original, MIT.

A reference guide for Anthropic’s Claude platform, including its API, models, prompt caching, tool use, and other platform features.

In plain words
What is it for?
Use it when working with Claude APIs, model selection, function calling, extended thinking, batch jobs, file handling, or citations.
Why use it?
It gives different engineering roles shared, current knowledge for designing and building with Claude services.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; positional $N argument; mentions Claude Code.

Part of the etyb plugin — 14 skills, 5 agents, 4 hooks shipped together

Good fit Use it when working with Claude APIs, model selection, function calling, extended thinking, batch jobs, file handling, or citations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/e-t-y-b/etyb-skills/anthropic-claude
Install

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.

Any agent
npx skills add e-t-y-b/etyb-skills --skill anthropic-claude
Clone the repo
git clone --depth 1 https://github.com/e-t-y-b/etyb-skills

Made for: Claude Code.

Or install etyb, the plugin that ships this one along with the rest of its 14 skills, 5 agents, 4 hooks.

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 stack-anthropic-claude

README.md
[![agentmods](https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/anthropic-claude/github.svg)](https://agentmods.dev/skills/e-t-y-b/etyb-skills/anthropic-claude)
Your own site
<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/anthropic-claude"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/anthropic-claude/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 stack-anthropic-claude

Your own site · 80×15
<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/anthropic-claude"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/anthropic-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 301 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,242 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00301 $0.04242
Opus 5 $0.00151 $0.02121
Sonnet 5 $0.00060 $0.00848
Haiku 4.5 $0.00030 $0.00424

Measured 12d ago against content hash c544c1db72ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

stack-anthropic-claude 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 12d 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.

stacks/anthropic-claude/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anthropic Claude Stack — Team Briefing

This is a knowledge overlay, not a new specialist. The existing ETYB team does the work — backend-architect writes the backend code, devops-engineer wires the deploys, security-engineer enforces the boundary. This pack tells each role where the current Anthropic Claude knowledge lives.

Where the full briefing lives

The full Stack briefing lives in this same folder. Per-product and per-role pages are siblings of this SKILL.md. Every page carries last_verified_on stamps and authoritative-source URLs in its frontmatter; see skills/etyb/core/knowledge-currency.md for the drift-check protocol that uses them.

  • Stack briefing: stacks/anthropic-claude/index.md
  • Per-product pages: stacks/anthropic-claude/<product>.md — one per entry in products_covered above
  • Per-role views: stacks/anthropic-claude/<role>.md — one per role in applies_to_roles above

When ETYB is installed locally these are read directly from disk. For third-party agents without the install, the same content is reachable as raw markdown at https://raw.githubusercontent.com/e-t-y-b/etyb-skills/main/stacks/anthropic-claude/<page>.md.

When delegate_to_skills (frontmatter above) lists a first-party vendor MCP/skill that's installed in the user's environment, ETYB defers to it first. The in-repo Stack content is the curated fallback.

What changed in 2025-2026 that older training data misses

Critical context — an LLM with a 2024 cutoff will get these wrong:

  • Model name rotation. Claude 3 → Claude 3.5 → Claude 3.7 → Claude 4 (May 2025) → Claude 4.1 → Claude 4.5 → Claude 4.6 → Claude 4.7 (Apr 2026) → Claude Opus 4.8 (May 2026) → the Claude 5 generation (Claude Fable 5 / Claude Mythos 5, June 2026; Claude Sonnet 5, June 2026). The current production default is Claude Sonnet 5 (claude-sonnet-5); the GA flagship is Claude Opus 4.8 (claude-opus-4-8); the Mythos-class tier above Opus is Claude Fable 5 (claude-fable-5, $10/$50 per MTok — GA with dual-use safety classifiers that can refuse cyber/bio-adjacent requests) and its classifier-free sibling Claude Mythos 5 (claude-mythos-5, limited to approved orgs in Project Glasswing). Older training data still recommends claude-3-opus-20240229 — retired. From the 4.6 generation onward, dateless model IDs are pinned snapshots (not floating aliases) — pin them as-is; never append a date suffix.
  • 1M context is standard now. Opus 4.6+, Sonnet 5/4.6, and Fable 5 ship a 1M-token context window at standard per-token pricing — the old >200K-input premium tier is gone. Still don't blindly stuff a million tokens into context — input cost scales linearly and most tasks don't need it.
  • Haiku 4.5 (Oct 2025) reset the cheap-tier envelope. Haiku at ~Sonnet-3.5 quality opens routing patterns that weren't viable before. Reconsider "Sonnet for everything" defaults.
  • Prompt caching is two-tier. 5-minute TTL (1.25x write cost, 0.1x read) is the default. 1-hour TTL (2x write cost, 0.1x read) is for stable long contexts. Up to 4 cache breakpoints per request. Cache reads are 90% off — architect for cacheability, not just for short prompts.
  • Extended Thinking became Adaptive Thinking. On current models (Opus 4.6+, Sonnet 5, Fable 5) use thinking: {type: "adaptive"} with output_config.effort — manual budget_tokens is deprecated on 4.6 and returns a 400 on Opus 4.7/4.8, Sonnet 5, and Fable 5 (it survives only on older models like Haiku 4.5). On Fable 5 thinking is always on. Thinking blocks must be passed back verbatim across tool-use round-trips, or you get errors; interleaving between tool calls is automatic under adaptive thinking.
  • Computer Use went from public beta (Oct 2024) to production-grade capability (2025-2026). Tool versions are dated (computer_20250124, computer_20251022...) and tied to model versions — you cannot mix-and-match. Requires a sandboxed VM; nobody runs this on a production server.
  • Memory tool shipped in 2025 as a first-class capability — the model can persist state across conversations via a managed memory store. This is distinct from "memory" in the conversational sense (context window). Memory belongs to a workspace/user scope you define.
  • Claude Agent SDK (@anthropic-ai/claude-agent-sdk, claude-agent-sdk on PyPI) launched in 2025 as the recommended way to build agentic loops on top of the Messages API. It owns the tool loop, retries, sub-agent spawning, and harness conventions. Don't roll your own agent loop in 2026 unless you have an explicit reason — use the SDK.
  • Skills as a first-class capability (2025-2026). A Skill is a SKILL.md (frontmatter + body) plus optional references/ and assets/. Skills auto-load based on description-trigger matching. This very ETYB pack is a Skill — you are reading proof that the system works.
  • MCP (Model Context Protocol) went from Nov-2024 launch to industry standard. Spec at the 2025-06-18 revision. Adopted by OpenAI, Google, Microsoft, JetBrains, Cursor, Zed, every major agent platform. SDKs in TypeScript, Python, Go, Java, Kotlin, Rust, C#. Tens of thousands of public MCP servers. If you're building agent tooling in 2026, build it as an MCP server first.

Read the full file on GitHub · 127 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. 12d ago First seen · 127 lines · 301 tokens per session scan A c544c1db72ba

Subscribe to this mod's changes

stack-anthropic-claude is a skill published in the GitHub repository e-t-y-b/etyb-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 301 tokens to every session and 4,242 once invoked, about $0.0015 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.

Related

Other skills, from other repositories

portaljs-architect

Recommend a data-portal architecture (storage, compute, catalog, access, hosting, metadata) from stated needs, then hand off to the build skills. The advisory entry point. Use when starting a new data-portal project and the underlying architecture has not yet been decided.

datopian/portaljs · 60 tokens

map

Build and commit a Cortex function knowledge graph — maps structural dependencies and domain intent relationships across all AI functions in the project. Supports --reduce (default on) for transitive reduction of the dependency graph.

Snowflake-Labs/cocoplus · 42 tokens

context-add

Guided wizard to capture or update organizational Snowflake/Cortex standards into .cocoplus/context/ .md. Presents a menu of 6 standard types, collects answers via multi-turn dialogue, and commits the file.

Snowflake-Labs/cocoplus · 48 tokens

cocolean

CocoLean — minimum viable Cortex surface discipline. Pre-build decision ladder and intensity mode management. Invoke with $lean, $lean lite, $lean full, or $lean ultra.

Snowflake-Labs/cocoplus · 41 tokens

test

Enter the Test phase of CocoBrew. Reads spec.md test requirements, generates test cases, executes SQL validation and quality checks, records results in test.md. Can be re-run without full rebuild. Requires Build phase completion.

Snowflake-Labs/cocoplus · 47 tokens

map-diff

Analyze the impact of staged git changes against the committed Cortex function knowledge graph — shows which downstream functions are affected before you commit.

Snowflake-Labs/cocoplus · 28 tokens