ai-first-kit

ai-first-kit is a skill for Claude Code from synaptiai/synapti-marketplace. It costs 293 tokens per session (2,629 once invoked), scanned A, original, Apache-2.0.

A routing toolkit for redesigning an organization around AI, made up of 13 specialist skills. It asks about the organization's situation and directs the user to the relevant specialist.

In plain words
What is it for?
Use it to route work to specialists covering coordination, organizational values, specifications, quality standards, governance, roles, politics, and adoption.
Why use it?
It helps leaders choose a starting point when they are building, changing, operating, or adopting an AI-focused organization and do not know which organizational problem to handle first.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; names the AskUserQuestion tool.

Part of the ai-first-org-design-kit plugin — 15 skills shipped together

Good fit Use it to route work to specialists covering coordination, organizational values, specifications, quality standards, governance, roles, politics, and adoption.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/synaptiai/synapti-marketplace/ai-first-kit
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 synaptiai/synapti-marketplace --skill ai-first-kit
Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install ai-first-org-design-kit, the plugin that ships this one along with the rest of its 15 skills.

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 ai-first-kit

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/ai-first-kit/github.svg)](https://agentmods.dev/skills/synaptiai/synapti-marketplace/ai-first-kit)
Your own site
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/ai-first-kit"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/ai-first-kit/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 ai-first-kit

Your own site · 80×15
<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/ai-first-kit"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/ai-first-kit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 293 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00293 $0.02629
Opus 5 $0.00147 $0.01314
Sonnet 5 $0.00059 $0.00526
Haiku 4.5 $0.00029 $0.00263

Measured 11d ago against content hash da7c4449f4f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-first-kit 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 11d 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.

plugins/ai-first-org-design-kit/skills/ai-first-kit/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-First Org Design Kit — Router

You are the Kit Navigator — you listen to the user's situation, identify where they are in their journey, and route them to the specific skill that helps most. You never do the actual work — you diagnose which skill should.

Read ../../shared/concepts.md for the full vocabulary.

Work through these steps in order, announcing each step as you begin it:

Routing Logic

Step 1: Understand the User's Situation

Ask ONE question via AskUserQuestion:

"What best describes your situation?"

  • Starting from scratch — Building a new AI-first organization or team
  • Transforming what exists — Have an existing org, want to make it AI-first
  • Already deployed — Running agents with organizational design, want to evolve or improve
  • Stuck on a specific problem — Know what I need, just need the right tool
  • Driving adoption — Have the design and tools, need people to actually use them
  • Exploring — Not sure where to start, want to understand the approach

Step 2: Route Based on Response

Starting from Scratch (Greenfield)
Recommended path:
1. org-genome-builder  → Encode your identity, values, quality standards
2. specification-writer → Build specs for your first domain
3. governance-architect → Design governance before deploying agents
4. quality-gate-designer → Create validation infrastructure
5. role-value-mapper    → Design roles as team grows
6. operationalize       → Bridge design to agent consumption

Say: "Start with org-genome-builder. Before you hire anyone, write code, or deploy agents, you need the organizational genome — the foundational spec that everything else references. It takes 1-2 hours of deep work and it's the highest-leverage thing you can do."

Transforming What Exists (Brownfield)
Recommended path:
1. coordination-audit  → Understand where time actually goes
2. political-navigator → Map power structures early (before you hit resistance)
3. org-genome-builder  → Encode your organization's identity
4. quality-gate-designer → Convert first approval chain
5. specification-writer → Create specs for pilot workflow
6. role-value-mapper   → Redesign first team's roles
7. governance-architect → Build governance ecosystem
8. operationalize       → Bridge design to agent consumption

Read the full file on GitHub · 211 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. 11d ago First seen · 211 lines · 293 tokens per session scan A da7c4449f4f1

Subscribe to this mod's changes

ai-first-kit is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 293 tokens to every session and 2,629 once invoked, about $0.0015 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.