agentmods.dev

gptbots-agent-skill

gptbots-agent-skill is a skill for Claude Code, Codex from GPTBOTS/Agent-Skills. It costs 136 tokens per session (5,987 once invoked), scanned A, original, MIT.

A skill for creating, reading, updating, and checking GPTBots agents and workflows. GPTBots is a platform for building chatbots, while .bot and .flow files store their configurations.

In plain words
What is it for?
Use it to build or optimize agents and workflows, validate their configuration files, run published ones through the API, test retrieval from knowledge bases, schedule runs, and manage their data.
Why use it?
It removes the need to edit these configuration files or call the GPTBots API manually for common setup and testing work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo changed 1mo ago A scan 136 tokens original MIT

Good fit Use it to build or optimize agents and workflows, validate their configuration files, run published ones through the API, test retrieval from knowledge bases, schedule runs, and manage their data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gptbots/agent-skills/gptbots-agent-skill
View source ↗ GPTBOTS/Agent-Skills
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 GPTBOTS/Agent-Skills --skill gptbots-agent-skill
Clone the repo
git clone --depth 1 https://github.com/GPTBOTS/Agent-Skills

Made for: Claude Code, Codex.

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 gptbots-agent-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/gptbots/agent-skills/gptbots-agent-skill/github.svg)](https://agentmods.dev/skills/gptbots/agent-skills/gptbots-agent-skill)
Your own site
<a href="https://agentmods.dev/skills/gptbots/agent-skills/gptbots-agent-skill"><img src="https://agentmods.dev/badge/skills/gptbots/agent-skills/gptbots-agent-skill/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 gptbots-agent-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/gptbots/agent-skills/gptbots-agent-skill"><img src="https://agentmods.dev/badge/skills/gptbots/agent-skills/gptbots-agent-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,987 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 $0.00136 $0.05987
Opus 5.5 $0.00054 $0.02395
Sonnet 5.5 $0.00027 $0.01197
Haiku 4.5 $0.00014 $0.00599

Measured 1mo ago against content hash d98615bc13fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gptbots-agent-skill 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 1mo ago.

The scan reads SKILL.md. This mod also ships 26 executable files (scripts/build_gptbots_agent.py, scripts/build_gptbots_audioagent.py, scripts/build_gptbots_config.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

gptbots-agent-skill/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPTBots Skill

A platform-level skill for working with GPTBots (https://www.gptbots.ai) Agents and Workflows.

Five target types, one per reference. Identify the type first (botType in the file, or from the user's scenario), then read only that type's reference — each one carries its own schema, invariants and builder:

type botType build/optimize with when
Agent QuestionAnswer references/create-gptbots-agent.md direct FAQ / RAG Q&A — fast and predictable
FlowAgent Flow references/create-gptbots-flowagent.md a reusable, deterministic business process you draw as a graph
LoopAgent LoopAgent references/create-gptbots-loopagent.md (+ loopagent-runtime.md) open-ended, multi-step, tool-heavy support/automation — the model picks the path at runtime
Audio Agent Audio references/create-gptbots-audioagent.md voice / telephony conversations (realtime or ASR→LLM→TTS)
Workflow Workflow references/create-gptbots-workflow.md a standalone orchestrated pipeline (.flow)

Use this skill to:

  • Read / update / optimize an Agent or Workflow config from a user-provided .bot or .flow file.
  • Create a new QuestionAnswer, FlowAgent, Audio Agent or Workflow from scratch (scenario + requirements → importable .bot / .flow). LoopAgent updates require an existing platform export and preserve its clawRule.
  • Create a new Agent / Workflow / Tool / MCP / Skill on the platform, and look up model version IDs, with the account-level DevKey/DevSecret APIs — see references/org-devkey-api.md. Org-level Skills are created and updated from a .skill/.zip package (/v1/org/skill/{create,update}; an update goes live at once).
  • Update, publish and roll back an existing Agent/Workflow's version, and create / update a LoopAgent's private Skills (/v1/agent/skill/{create,update}), via that target's own API Key (needs version-management permission, granted in the console) — see references/version-manage-api.md.
  • Drive a published Agent/Workflow via the public Open API for evaluation, quality assessment, RAG testing, scheduled triggering, and data/knowledge-base management.
  • Organize raw documents into import-ready knowledge-base files (Document / Table / Q&A) and advise on chunking, metadata, and retrieval tuning.

Read the full file on GitHub · 186 lines

Files

What ships with it

44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago Changed · +7 lines · -128 tokens per session d98615bc13fb
  2. 1mo ago Changed · +99 lines · +128 tokens per session 4f4aaa783a87
  3. 2mo ago First seen · 80 lines · 136 tokens per session scan A 5584a9bc4f1b

Subscribe to this mod's changes

gptbots-agent-skill is a skill published in the GitHub repository GPTBOTS/Agent-Skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 5,987 once invoked, about $0.0005 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 2026-08-31.

Building agents
Related

gptbots-agent-skill compared with skills from other repositories

gptbots-agent-skill next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gptbots-agent-skillGPTBOTS/Agent-SkillsSkill21mo agoMITA136Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex