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 humandesignai/human-design-ai-mcp --skill human-design-aigit clone --depth 1 https://github.com/humandesignai/human-design-ai-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/skills/humandesignai/human-design-ai-mcp/human-design-ai)<a href="https://agentmods.dev/skills/humandesignai/human-design-ai-mcp/human-design-ai"><img src="https://agentmods.dev/badge/skills/humandesignai/human-design-ai-mcp/human-design-ai/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/humandesignai/human-design-ai-mcp/human-design-ai"><img src="https://agentmods.dev/badge/skills/humandesignai/human-design-ai-mcp/human-design-ai.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 | $0.00045 | $0.01790 |
| Opus 5 | $0.00023 | $0.00895 |
| Sonnet 5 | $0.00009 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
human-design-ai 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 7d 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.
HumanDesign.ai
Use the official HumanDesign.ai MCP for requests involving the signed-in user's individual charts, saved composite relationship charts, library, existing reports, operations, account usage, or other account-connected capabilities that the live catalog advertises. A separate API-key connection can expose new composite calculations, transits, and public-figure search according to its API tier.
Connect and establish context
- Use the OAuth connection supplied by the MCP server. Never ask the user to paste passwords, OAuth tokens, refresh tokens, API keys, integration secrets, or signed URLs into chat.
- When available, call
account_get_contextbefore account-connected work. Use only tools returned by discovery; the server filters tools by server-derived capability grants, membership, workspace role, ownership, and entitlements. - The selected account or workspace is the data boundary for this connection. It is not an extra permission grant. A Builder grant covers eligible projects beneath that boundary, while ownership and role are still revalidated on every request.
- Prefer read-only discovery before proposing a mutation or consuming operation.
Membership-aware boundaries
- Free: view and render the user's own primary chart. Creating it through MCP is available only when the live catalog advertises
chart_generate; otherwise send the user through normal HumanDesign.ai onboarding. - Individual (internal identifier:
solo): the Free chart boundary plus account usage information; it does not grant access to other people's charts, saved composites, the wider library, or reports. - Personal: the minimum membership that may expose wider authorized charts, saved composites, the wider library, and already-owned reports according to the live catalog.
- Pro: Personal capabilities plus entitled professional workspaces.
- Website Builder tools appear only when HumanDesign.ai has enabled the Builder for the user's account, and only when
tools/listadvertises them. - The live server is authoritative. Never infer access from marketing copy or claim that a membership unlocks a tool unless the refreshed tool list or server response confirms it.
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.
- 7d ago Changed · +12 lines · +6 tokens per session 0b316c2bb6ff
- 12d ago First seen · 65 lines · 39 tokens per session scan A 79c45e87b5ed
human-design-ai is a skill published in the GitHub repository humandesignai/human-design-ai-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 1,790 once invoked, about $0.0002 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 skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
grounded-citations
Ground answers and documents in cited, verifiable sources.
hermes-agent-skill-authoring
Author in-repo SKILL.md files: frontmatter and structure.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
flash-attention
Speed up long-sequence transformer training and inference.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).