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 naveedharri/benai-skills --skill agent-buildergit clone --depth 1 https://github.com/naveedharri/benai-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/skills/naveedharri/benai-skills/agent-builder)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/agent-builder"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/agent-builder/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/naveedharri/benai-skills/agent-builder"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 78 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 156 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 54 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 69 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 119 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.02674 |
| Opus 5 | $0.00000 | $0.01337 |
| Sonnet 5 | $0.00000 | $0.00535 |
| Haiku 4.5 | $0.00000 | $0.00267 |
Grade A, and why
agent-builder 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 10d 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.
2. Do not list "Step 1, Step 2, …" in chat. Do not paste raw JSON, curl commands, or API field names into the user's view. Those exist only in the references for your own use. How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Builder
Build Anthropic Managed Agents through a friendly, non-technical conversation. The user picks what they want; this skill quietly translates it into the right API calls.
When This Skill Loads
- Silently read every file in
references/. Do not narrate this. - Do not list "Step 1, Step 2, …" in chat. Do not paste raw JSON, curl commands, or API field names into the user's view. Those exist only in the references for your own use.
- Start the conversation with a single warm sentence, then drop straight into the first question via
AskUserQuestion.
Opener (example, vary as needed):
"Let's build your agent. A few quick questions and I'll set everything up for you."
How To Drive The Conversation
Every branching question MUST go through AskUserQuestion, never plain chat. Plain chat is reserved for short confirmations and the final summary. Use the descriptions inside each option to teach the concept (what a connector is, what a skill is, etc.) so the user never has to know the underlying terms.
Run the questions in this order. Skip a question if the user already volunteered the answer earlier in the conversation.
Q1. What kind of agent are you building?
Use AskUserQuestion. Header: Agent type. Options (single-select):
- Research & analysis. Reads sources on the web or in your tools, summarizes, finds patterns.
- Content creation. Drafts posts, emails, scripts, documents.
- Operations & automation. Handles tasks across your apps (Slack, Notion, CRM, etc.).
- Custom. Describe it yourself.
If "Custom", follow up with a single open question: "In one sentence, what should this agent do?"
Internally, use the answer to seed a short system prompt. The user never sees the word "system prompt".
Q2. Which apps should it connect to?
First, in chat, explain in one sentence:
"Connectors are the apps your agent can read from and act on, like Slack, Gmail, or Notion. Pick whichever this agent needs."
Then use AskUserQuestion with multiSelect: true. Header: Connectors. Options:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 216 lines · 0 tokens per session scan A c69929e69169
agent-builder is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,674 tokens. 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 2026-08-30.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
finance-investor-relations
An investor-relations tool for preparing pitch decks and three-year financial models for fundraising. An IR, or investor-relations, deck explains a company to potential investors, while the model covers sales, profit, cash flow, and valuation.