What is agent-builder?

A guide for creating specialised AI agents for Claude Code projects. It helps define agent roles and add agents to a project's .claude/agents/ folder.

Designing agent roles, creating new agents, building agent teams, and adding agents to Claude Code projects.

It removes the guesswork from deciding what an agent should do and how to organise multiple agents in a project.

How fltman/create-agentic-product configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fltman/create-agentic-product. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/fltman/create-agentic-product/main/.claude/skills/agent-builder/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/fltman/create-agentic-product

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fltman/create-agentic-product/agent-builder/github.svg)](https://agentmods.dev/skills/fltman/create-agentic-product/agent-builder)

Your own site

<a href="https://agentmods.dev/skills/fltman/create-agentic-product/agent-builder"><img src="https://agentmods.dev/badge/skills/fltman/create-agentic-product/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fltman/create-agentic-product/agent-builder"><img src="https://agentmods.dev/badge/skills/fltman/create-agentic-product/agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,903 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.01903
Opus 5.5	$0.00020	$0.00761
Sonnet 5.5	$0.00010	$0.00381
Haiku 4.5	$0.00005	$0.00190

Measured 2mo ago against content hash ecf5fb6d38b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-builder 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 2mo 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.

.claude/skills/agent-builder/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Builder

Bygg specialiserade AI-agenter for Claude Code-projekt. Varje agent blir en .md-fil i .claude/agents/ som Claude Code automatiskt kan delegera till.

Workflow

Steg 1: Förstå behovet

Fråga (om det inte redan framgår):

Projekttyp - Vad bygger ni? (app, produkt, content, etc.)
Agentens roll - Vad ska agenten göra?
Samarbete - Vilka andra agenter finns/planeras?
Språk - Ska agenten skriva på svenska eller engelska?

Steg 2: Designa agenten

Varje agent-fil följer detta format:

---
name: agent-namn-med-bindestreck
description: Kort beskrivning. Use PROACTIVELY when [trigger]. Handles [ansvar].
tools: [välj från listan nedan]
model: [inherit|sonnet|opus|haiku]
---

# Agentens huvudinnehåll

Steg 3: Välj rätt tools

Tillgängliga verktyg:

Behov	Tools
Bara läsa/researcha	`Read, Grep, Glob`
Läsa + terminalen	`Read, Grep, Glob, Bash`
Skriva/redigera kod	`Read, Write, Edit, Grep, Glob, Bash`
Webresearch	`Read, WebSearch, WebFetch`
Koordinera andra agenter	`Read, Write, Agent(agent1, agent2), Grep, Glob`
Full access	`Read, Write, Edit, Bash, Grep, Glob, WebSearch, WebFetch`

Följande verktyg rekommenderas för maximal effektivitet: tools: Read, Write, Edit, Bash, MultiEdit, Task, TodoWrite, WebFetch, WebSearch

Steg 4: Välj rätt modell

Modell	Använd för
`opus`	Komplex kreativ/strategisk tankeverksamhet, projektledning, arkitektur
`sonnet`	Balans mellan snabbhet och kvalitet, bra default
`haiku`	Snabba, enkla uppgifter, sökningar, validering
`inherit`	Ärver från föräldrakonversationen

Steg 5: Skriv agentens prompt

Följ denna struktur:

# [Rollnamn]

[1-2 meningar om vem agenten är och vad den gör]

## Din Roll

Du ansvarar för:
- **[Ansvar 1]**: Kort beskrivning
- **[Ansvar 2]**: Kort beskrivning
- **[Ansvar 3]**: Kort beskrivning

## Arbetsprocess

### Vid start
1. [Vad agenten gör först — t.ex. läs log, förstå kontext]
2. [Analysera uppgiften]
3. [Börja arbeta]

### Under arbetet
- [Princip 1]
- [Princip 2]
- [Kvalitetskrav]

### Vid leverans
- [Outputformat]
- [Verifieringssteg]

## Riktlinjer
- [Viktig regel 1]
- [Viktig regel 2]
- [Begränsningar]

## Samarbete med andra agenter
[Om relevant — beskriv hur agenten interagerar med teamet]

Read the full file on GitHub · 238 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.

2mo ago First seen · 238 lines · 49 tokens per session scan A ecf5fb6d38b3

Subscribe to this mod's changes

agent-builder is a skill published in the GitHub repository fltman/create-agentic-product (48 stars, last pushed 9d ago), licensed MIT. It adds 49 tokens to every session and 1,903 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Building agents

agent-builder next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-builderfltman/create-agentic-product	Skill	48	9d ago	MIT	A	49	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

create-agentic-product: Skill for Claude Code