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 skills add frankxai/claude-skills-library --skill partner-anthropicgit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/skills/frankxai/claude-skills-library/partner-anthropic)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/partner-anthropic"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/partner-anthropic/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.
<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/partner-anthropic"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/partner-anthropic.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00069 | $0.02006 |
| Opus 5.5 | $0.00028 | $0.00802 |
| Sonnet 5.5 | $0.00014 | $0.00401 |
| Haiku 4.5 | $0.00007 | $0.00201 |
Grade A, and why
partner-anthropic 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anthropic — Partner Intelligence
Current state (as of 2026-05-17)
The Claude 4 family is the current shipping line — Opus 4.7 at the top (extended thinking + 1M context), Sonnet 4.6 in the middle, Haiku 4.5 at the bottom (to verify exact release dates beyond Frank's Jan 2026 knowledge cutoff). Claude Code is now a first-class CLI with SDK bindings and a stable skill format. The Model Context Protocol (MCP) — owned and stewarded by Anthropic — has graduated from spec to ecosystem standard, with first-party tooling from Vercel, Cursor, and Codex consuming the same wire format. Claude for Work and Claude for Enterprise tiers continue to anchor the commercial lane.
Product map
- Claude (model family) — Opus 4.7 (reasoning + 1M context), Sonnet 4.6 (balanced), Haiku 4.5 (fast). Frank works against Opus 4.7 by default.
- Claude Code (CLI + SDK) — the agentic build harness. Stable skills/agents/commands/hooks format. The harness underneath every shipped FrankX repo.
- Claude API — direct API access via
@anthropic-ai/sdk(TS) andanthropic(Python). Prompt caching, tool use, vision, batch, files, citations, memory. - Claude Agent SDK — managed-agent framework for long-running autonomous loops. Sibling lane to Vercel AI SDK (web) and Google ADK (enterprise) in the Starlight three-lane portfolio.
- Claude for Work — team tier with shared chats, projects, and admin controls.
- Claude for Enterprise — SSO, audit, data residency, expanded context, enterprise procurement.
- Model Context Protocol (MCP) — open spec owned by Anthropic. Servers expose tools/resources/prompts over stdio or HTTP. Frank ships SIS as a 31-tool MCP server.
- Claude Code skills marketplace — community + first-party skills (
vercel:*,code-review:*,superpowers:*,agent-sdk-dev:*, etc.). - Open-source artifacts —
@anthropic-ai/sdk(MIT),claude-code(proprietary CLI, MIT skills), MCP reference servers and SDKs (MIT).
Pricing tiers (May 2026, to verify against current pricing page)
- Free (Claude.ai) — Sonnet access, daily message limit.
- Pro — $20/mo individual. Higher limits, Opus access, Projects.
- Max — $100-200/mo tier (to verify) for heavy Opus users + Claude Code.
- Team — $25-30/seat/mo (to verify), 5-seat minimum, shared Projects.
- Enterprise — contact sales. SSO, audit, data residency, expanded context window, custom retention.
- API — pay-per-token. Opus 4.7 ~$15/$75 per million input/output (to verify). Prompt caching cuts repeat-prompt cost 90%. Batch API 50% discount.
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.
- 1mo ago First seen · 77 lines · 69 tokens per session scan A d619dae24fee
partner-anthropic is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 2,006 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
prompt-refiner
Lints an existing user-supplied prompt for prompt-engineering defects and prompt-injection risks. Produces a diagnostic report with rule IDs, severity, line/column, quoted evidence, rationale, and optional JSON output. Does not rewrite prompts or impose prompt frameworks.
prompt-modeler
Generate structured strategic prompts with diagnostic and multiple options. Triggers on: /modelar-prompt.
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
prompt-engineering-outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
ai-context-primer
Build the context an AI needs to do a task well — the background, constraints, examples, and format it can't guess — so you get a great result on the first try instead of a generic one you have to keep correcting. Use when asked why does AI give me generic answers, how do I give AI better context, my AI results are…