onboard-product

onboard-product is a skill for Claude Code from EliBarak12/Elliot. It costs 67 tokens per session (1,162 once invoked), scanned C, original, MIT.

A guided interview for turning an API or database into tools that AI agents can use. It first asks what the product is and what agents should do, then uses those answers to shape the connector.

In plain words
What is it for?
Use it when making an existing API or database agent-ready. It helps gather product context, agent users, and intended actions before importing an API description or designing tools.
Why use it?
It avoids designing tools based only on the data source, which may produce tools that do not match the product’s intended use. The interview captures the owner’s goals before tool design begins.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the elliot plugin — 10 skills, 2 hooks, 1 MCP server shipped together

Good fit Use it when making an existing API or database agent-ready. It helps gather product context, agent users, and intended actions before importing an API description or designing tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elibarak12/elliot/onboard-product
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 EliBarak12/Elliot --skill onboard-product
Clone the repo
git clone --depth 1 https://github.com/EliBarak12/Elliot

Made for: Claude Code.

Or install elliot, the plugin that ships this one along with the rest of its 10 skills, 2 hooks, 1 MCP server.

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 onboard-product

README.md
[![agentmods](https://agentmods.dev/badge/skills/elibarak12/elliot/onboard-product/github.svg)](https://agentmods.dev/skills/elibarak12/elliot/onboard-product)
Your own site
<a href="https://agentmods.dev/skills/elibarak12/elliot/onboard-product"><img src="https://agentmods.dev/badge/skills/elibarak12/elliot/onboard-product/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 onboard-product

Your own site · 80×15
<a href="https://agentmods.dev/skills/elibarak12/elliot/onboard-product"><img src="https://agentmods.dev/badge/skills/elibarak12/elliot/onboard-product.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,162 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00067 $0.01162
Opus 5 $0.00034 $0.00581
Sonnet 5 $0.00013 $0.00232
Haiku 4.5 $0.00007 $0.00116

Measured 12d ago against content hash 1f9712487645, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

onboard-product scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

Elliot plugin: !`curl -s http://localhost:3000/health 2>/dev/null | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('status','unknown'))" 2>/dev/null || echo "not running — start Elliot first: make dev"`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Elliot plugin: !`curl -s http://localhost:3000/health 2>/dev/null | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('status','unknown'))" 2>/dev/null || echo "not running — start Elliot first: make dev"`
skills/onboard-product/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onboard Product Workflow

You are onboarding a user's product into Elliot. Do not look at their data and decide the tools yourself. The whole point of this workflow is that the tools reflect what the user wants agents to do. Interview first, design second.

Workspace state

Elliot plugin: !curl -s http://localhost:3000/health 2>/dev/null | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('status','unknown'))" 2>/dev/null || echo "not running — start Elliot first: make dev"

Steps

1. Import the user's API collection

Ask the user for whatever description of their API they already have:

  • An OpenAPI 3.x spec (URL or JSON), or
  • A Postman Collection export (JSON), or
  • Raw docs / curl examples — if so, help them turn it into one of the above.

Call elliot_import_api_collection with the spec/collection. It returns a set of proposed tools with token-risk hints. Do not build from this yet — it is input to the interview, not the answer.

2. Interview the user

Ask these questions, one topic at a time, in plain language. Wait for answers.

  • Who are the agents? What product will call these tools (support bot, internal copilot, a customer-facing assistant)?
  • What jobs should agents do? Get 3-6 concrete tasks, phrased as a user goal ("find a customer's open invoices and email a reminder"). These matter most — they become the audit seeds later.
  • What should be exposed vs hidden? Which operations agents should have, and which to keep off-limits.
  • What is destructive? Which operations mutate data or are irreversible and should require a confirmation gate.
  • What is sensitive? Field names that must never reach an agent (PII, secrets, internal flags).
  • Whose credentials? Does every caller share one account/key (a service account, public data), or should each end user act as themselves with their own token (GitHub, Slack, Gmail, anything per-account)? If per-user, the source uses auth.scope: "per_user" and each caller connects via OAuth — don't bake in one shared token or add a token parameter to a tool. See elliot://docs/authentication.
  • Scale? Roughly how much data a typical result spans.

Read the full file on GitHub · 88 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 · 88 lines · 67 tokens per session scan C 1f9712487645

Subscribe to this mod's changes

onboard-product is a skill published in the GitHub repository EliBarak12/Elliot (11 stars, last pushed 12d ago), licensed MIT. It adds 67 tokens to every session and 1,162 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.