create

A guide for creating an agent that other people in an organisation can use. It explains how to name the agent, write its instructions, grant tools and skills, limit its knowledge, and test it in chat.

In plain words
What is it for?
Building support-triage agents or other specialised agents, configuring their visibility and tools, and trying them before sharing them.
Why use it?
It turns an empty agent setup into a usable assistant with a defined purpose and controlled access.

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/tale-project/tale/create
Clone the repo
git clone --depth 1 https://github.com/tale-project/tale
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,838 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 $0.00037 $0.01838
Opus 5 $0.00018 $0.00919
Sonnet 5 $0.00007 $0.00368
Haiku 4.5 $0.00004 $0.00184

Measured yesterday against content hash cced6cd954d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create 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.

docs/de/platform/agents/create.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diese Anleitung führt vom leeren Dialog zu einem Agenten, den deine Kolleginnen auswählen können. Am Ende steht eine Persona, die ihre Domäne kennt, die Tools hat, um mit dem Gelesenen etwas anzufangen, und aus jedem Chat deiner Organisation erreichbar ist. Rechne mit rund fünfzehn Minuten.

Als durchgehendes Beispiel dient ein Agent für die Support-Triage — derselbe, den Agent-Konzepte einführt. Setz ruhig deine eigene Domäne ein; keiner der Schritte hängt am Beispiel.

Bevor du anfängst

Zwei Dinge sollten stehen:

  • Deine Organisation hat mindestens einen Provider-Zugang unter Einstellungen > Provider. Der Agent selbst nennt kein Modell — wer eine Nachricht abschickt, wählt es im Composer —, aber der Composer hat nichts anzubieten, solange kein Zugang existiert. In der Cloud ist einer voreingestellt; wer selbst hostet, folgt Konfiguration → Provider.
  • Du hast hier mindestens die Rolle Editor. Unter Mitglieder und Rollen siehst du nach, falls du unsicher bist.

Schritt 1 — Benennen und festlegen, wer ihn sieht

Öffne Agenten in der Seitenleiste und lege einen neuen an. Der Dialog fragt nach einem Namen — der eindeutigen ID, die in Links und in der API auftaucht und sich später nicht mehr ändern lässt, also lieber sprechend und klein geschrieben, support-triage statt agent2 — dazu nach einem Anzeigenamen, unter dem das Team ihm begegnet, und einer kurzen Beschreibung. Bestätige, und der Editor öffnet sich auf Allgemein.

Auf Allgemein sitzt die Identität: Anzeigename, Beschreibung, ein Icon und die Sichtbarkeit des Agenten. Halte ihn privat, solange du noch an ihm formst, dann kommst nur du heran; gib ihn für die Organisation frei, und jedes Mitglied kann ihn im Composer auswählen. Ein privater Agent hält einen Besitzer fest, und das bist du — ein Agent, den niemand besitzt und niemand sieht, wäre für niemanden erreichbar.

Read the full file on GitHub · 73 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 · 73 lines · 37 tokens per session scan A cced6cd954d7

Subscribe to this mod's changes

create is an agent published in the GitHub repository tale-project/tale (23 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,838 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 2026-08-30.

Related

Other agents, from other repositories

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

bestmode

You are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user.

raphaelmansuy/edgequake · 0 tokens

workflow-debugger

Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.

growthxai/output · 40 tokens

electron-e2e-test-runner

Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…

sahithvibudhi/vibe-tree · 365 tokens

harness-interpreter

Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.

Goldziher/basemind · 44 tokens