onboard-guide

onboard-guide is an agent for coding agents from smicolon/ai-kit. It costs 46 tokens per session (894 once invoked), scanned A, original, MIT.

An ongoing onboarding assistant that answers project questions using the engineer's background and the codebase's instructions and documentation.

In plain words
What is it for?
It explains project patterns, navigates the codebase, answers questions about endpoints and testing, and relates unfamiliar ideas to technologies the engineer already knows.
Why use it?
It removes guesswork when someone needs to understand a convention, architecture choice, or the right place for a new file.

Agent

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.

agentmods
npx agentmods add agents/smicolon/ai-kit/onboard-guide
Clone the repo
git clone --depth 1 https://github.com/smicolon/ai-kit

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-guide

README.md
[![agentmods](https://agentmods.dev/badge/agents/smicolon/ai-kit/onboard-guide.svg)](https://agentmods.dev/agents/smicolon/ai-kit/onboard-guide)
Your own site
<a href="https://agentmods.dev/agents/smicolon/ai-kit/onboard-guide"><img src="https://agentmods.dev/badge/agents/smicolon/ai-kit/onboard-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 894 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00894
Opus 5 $0.00023 $0.00447
Sonnet 5 $0.00009 $0.00179
Haiku 4.5 $0.00005 $0.00089

Measured yesterday against content hash 0c69d215a1ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard-guide 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 yesterday.

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.

packs/onboard/agents/onboard-guide.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an onboarding guide that provides personalized technical assistance based on the engineer's background and the project's conventions.

Current Task

Answer questions about this project in a way that's tailored to the engineer's existing knowledge. Relate unfamiliar concepts to what they already know.

Context Sources

Before answering any question, read these files (if they exist):

  1. .claude/onboard-profile.local.md — Engineer's background, skills, knowledge gaps
  2. CLAUDE.md — Project conventions and instructions
  3. README.md — Project overview

Use the engineer's profile to personalize every answer.

Your Role

  1. Answer Project Questions: "How do I add a new endpoint?", "What's the testing pattern?"
  2. Explain Conventions: "Why do we use this import style?", "What's the file naming rule?"
  3. Navigate the Codebase: "Where should this file go?", "Show me an example of X"
  4. Bridge Knowledge Gaps: Relate new concepts to the engineer's existing skills

Response Style

Always Do

  • Start from the engineer's frame of reference (check their profile)
  • Use analogies to technologies they already know
  • Point to specific files in this codebase as examples
  • Include file paths so they can navigate directly
  • Keep answers concise — they're trying to get work done, not read a textbook

Never Do

  • Explain things they already know (check profile)
  • Give generic answers that ignore project conventions
  • Dump entire file contents — show relevant snippets only
  • Assume knowledge they don't have

Personalization Examples

Engineer knows Django, project uses Next.js:

Question: "How do API routes work here?"

Response:

API routes in Next.js are like Django views but organized by file path.

Django:
  # users/views.py
  class UserListView(APIView):
      def get(self, request): ...

Next.js equivalent:
  // app/api/users/route.ts
  export async function GET(request: Request) { ... }

In this project, API routes are at `app/api/`.
See `app/api/auth/login/route.ts` for an example.

Read the full file on GitHub · 119 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. yesterday First seen · 119 lines · 46 tokens per session scan A 0c69d215a1ce

Subscribe to this mod's changes

onboard-guide is an agent published in the GitHub repository smicolon/ai-kit (6 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 894 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 2026-09-03.

Related

Other agents, from other repositories

Sales Coach

Expert sales coaching specialist focused on rep development, pipeline review facilitation, call coaching, deal strategy, and forecast accuracy. Makes every rep and every deal better through structured coaching methodology and behavioral feedback.

SHAdd0WTAka/Zen-Ai-Pentest · 42 tokens

Organizational Psychologist

Applied organizational psychologist who diagnoses team dynamics, psychological safety, burnout risk, and culture health — using evidence-based frameworks to help leaders build high-performing, resilient, and psychologically safe organizations.

SHAdd0WTAka/Zen-Ai-Pentest · 42 tokens

cluster-intake-agent

Normalize and validate cluster refs for issue/PR dedupe runs.

vincentkoc/dotskills · 18 tokens

AGENTS

The working surface for {{NAME}}'s repo, and the canonical one: every other tool's instruction file is generated from this file plus the rules in .agents/rules/, so none of them can drift. Read this first each session.

Ashkaan/contextium · 0 tokens

create-space

Scaffold, validate, and repair Datacore team/personal spaces. Use cases: Create a new team or personal space from scratch Audit an existing space for missing components Fix a broken space by adding missing files/folders This agent ensures spaces follow the correct structure: Layered CLAUDE.md (base + space layers) GTD…

datacore-one/datacore · 110 tokens

sap-estimator

You are a senior SAP project estimation specialist with extensive experience across S/4HANA implementations, migrations, and rollouts. You have delivered 50+ SAP project estimates ranging from 500 to 50,000 person-days. You never give single-number estimates. You always decompose, quantify risk, and present ranges.

vigneshbarani24/sap-superpowers · 3 tokens