generate-agent-config

generate-agent-config is a command for Claude Code from TheBeardedBearSAS/claude-craft. It costs 19 tokens per session (991 once invoked), scanned A, original, MIT.

A command guide for preparing the JSON request used to add an AI agent to a Paperclip company. It walks through the company, adapter, role, model, and budget details.

In plain words
What is it for?
Drafting an agent-hiring payload for Paperclip’s API or dashboard and checking the adapter-specific configuration.
Why use it?
It avoids assuming that agents can be created from a YAML file or with unsupported command-line options.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks shipped together

Good fit Drafting an agent-hiring payload for Paperclip’s API or dashboard and checking the adapter-specific configuration.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/thebeardedbearsas/claude-craft/generate-agent-config
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.

Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 hooks.

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 generate-agent-config

README.md
[![agentmods](https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/generate-agent-config/github.svg)](https://agentmods.dev/commands/thebeardedbearsas/claude-craft/generate-agent-config)
Your own site
<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/generate-agent-config"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/generate-agent-config/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 generate-agent-config

Your own site · 80×15
<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/generate-agent-config"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/generate-agent-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 991 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00019 $0.00991
Opus 5 $0.00010 $0.00495
Sonnet 5 $0.00004 $0.00198
Haiku 4.5 $0.00002 $0.00099

Measured 5d ago against content hash 5cd7c74884f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

generate-agent-config 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 5d 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.

curl -X POST "http://localhost:3100/companies/<companyId>/agents" \
Dev/i18n/de/Paperclip/commands/generate-agent-config.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Einen Paperclip-Agent-Hire entwerfen

Argumente

  1. agent-name (erforderlich) — kebab-case-Label für den neuen Agent (z.B. senior-coder, qa-bot)

MISSION

Einen wohlgeformten Payload für das Einstellen eines Paperclip-Agents produzieren. Paperclip (v2026.609.0) stellt Agents nicht aus einer .yaml-Datei via CLI ein — Hiring geschieht über das Dashboard oder POST /companies/:companyId/agents. Dieser Befehl entwirft den JSON-Payload und führt den Operator durch das Ausfüllen.

Vorgehen

1. Eingaben sammeln (interaktiv)

In Reihenfolge fragen:

  • Ziel-companyId (muss existieren — siehe /paperclip:setup-company oder paperclipai company list)
  • adapterType — einer der registrierten Typen (z.B. claude_local, codex_local, gemini_local, cursor_local, opencode_local, pi_local). Das agentConfigurationDoc des gewählten Adapters sagt, welche Sub-Felder akzeptiert werden.
  • Agent-Display-Name ($1)
  • Rolle / Titel (z.B. "Senior TypeScript engineer")
  • Zu assoziierendes Goal (optional; abrufen mit paperclipai company get --id <companyId>)
  • Modell-ID (muss in der models-Liste des Adapters sein)
  • Budget (Tokens, optional; eine harte Grenze setzen, wenn Enforcement gewünscht)
  • Adapter-spezifische Konfiguration: cwd, model, extraArgs, env, workspaceStrategy, timeoutSec, graceSec und adapter-spezifische Flags (z.B. dangerouslySkipPermissions für claude_local)

2. Den Payload emittieren

{
  "name": "{{AGENT_NAME}}",
  "displayName": "{{DISPLAY_NAME}}",
  "role": "{{ROLE}}",
  "goalId": "{{GOAL_ID_OR_NULL}}",
  "adapterType": "{{ADAPTER_TYPE}}",
  "adapterConfig": {
    "model": "{{MODEL_ID}}",
    "cwd": "{{CWD_OR_NULL}}",
    "timeoutSec": 900,
    "graceSec": 15,
    "extraArgs": [],
    "env": {},
    "workspaceStrategy": {
      "type": "git_worktree",
      "baseRef": "main"
    }
  },
  "budget": {
    "tokens": {{TOKEN_BUDGET_OR_NULL}}
  }
}

Die reale Form prüfen. Vor dem POSTen server/src/routes/agents.ts (oder die OpenAPI-Spec, die von der Instanz bereitgestellt wird) öffnen, um das exakte Schema zu bestätigen — das Obige spiegelt wider, was bei v2026.609.0 beobachtet wurde, aber Feldnamen können sich entwickeln.

Read the full file on GitHub · 93 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. 5d ago First seen · 93 lines · 19 tokens per session scan A 5cd7c74884f8

Subscribe to this mod's changes

generate-agent-config is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 991 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-03.