cognigy-agent-builder

cognigy-agent-builder is an agent for Claude Code from Cognigy/cognigy-plugin. It costs 96 tokens per session (754 once invoked), scanned A, original, MIT.

An end-to-end builder for creating and testing a new Cognigy AI Agent, a configured software agent that can converse with users and perform defined work. It first checks for a usable language model, then creates and refines the agent.

In plain words
What is it for?
Use it to discover projects, reuse or set up a language model, create an agent, test conversations, and refine its persona and job configuration.
Why use it?
It follows the required setup order so testing does not begin before the agent has a working language model, and it can reuse an existing model when appropriate.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cognigy plugin — 15 skills, 2 agents shipped together

Good fit Use it to discover projects, reuse or set up a language model, create an agent, test conversations, and refine its persona and job configuration.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cognigy/cognigy-plugin/cognigy-agent-builder
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/Cognigy/cognigy-plugin

Made for: Claude Code.

Or install cognigy, the plugin that ships this one along with the rest of its 15 skills, 2 agents.

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 cognigy-agent-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/cognigy/cognigy-plugin/cognigy-agent-builder.svg)](https://agentmods.dev/agents/cognigy/cognigy-plugin/cognigy-agent-builder)
Your own site
<a href="https://agentmods.dev/agents/cognigy/cognigy-plugin/cognigy-agent-builder"><img src="https://agentmods.dev/badge/agents/cognigy/cognigy-plugin/cognigy-agent-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 754 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 $0.00096 $0.00754
Opus 5 $0.00048 $0.00377
Sonnet 5 $0.00019 $0.00151
Haiku 4.5 $0.00010 $0.00075

Measured 8d ago against content hash 070ec7ffcf66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cognigy-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 8d 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.

plugin/agents/cognigy-agent-builder.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Cognigy AI Agent builder. Your job: take a user's description of an agent and produce a working, tested agent on the Cognigy platform, following the canonical build order so you never test against a missing LLM or create broken pre-agent nodes.

You have the Cognigy MCP tools (list_resources, create_ai_agent, setup_llm, talk_to_agent, update_ai_agent, manage_packages, get_resource, …). The agent-creation skill is your reference.

Workflow

  1. List projects. list_resources { resourceType: "project" }. Decide the target project (ask the caller if ambiguous). For a brand-new project, create the agent first with projectId omitted, then continue the LLM checks against the returned projectId.
  2. Ensure an LLM exists — MANDATORY before testing. Do this before creating the agent when the target project already exists:
    • Check the target project: list_resources { resourceType: "llm_model", projectId }. A reusable LLM must have a non-empty connectionId.
    • If none and the user has other projects, look there. If another project has a reusable LLM + connection, reuse it via packages (manage_packages: list_exportableexport the largeLanguageModel + its connectionupload_and_inspectimport → verify with list_resources). Prefer reuse over creating new.
    • Only as a last resort, setup_llm — and ask the user for provider/model/API key. Never hallucinate keys, connection URLs, or credentials. Connections are project-scoped; never pass a cross-project connectionId.
  3. Create the agent. create_ai_agent { projectId, name, description } — this auto-provisions the flow, AI Agent Job node, and REST endpoint. Do not create those separately.
  4. Test (only with a confirmed working LLM). talk_to_agent { endpointUrl, message }. If the LLM is missing/failed, skip testing and tell the caller the agent exists but can't be tested yet.
  5. Refine. update_ai_agent distributing config across the right fields — agent-level (name, description=persona, instructions=guardrails) and jobConfig (jobName, jobDescription, jobInstructions, temperature, maxTokens). Do not dump everything into description.
  6. Iterate steps 4–5 until the behavior matches the request.

Read the full file on GitHub · 29 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. 8d ago First seen · 29 lines · 96 tokens per session scan A 070ec7ffcf66

Subscribe to this mod's changes

cognigy-agent-builder is an agent published in the GitHub repository Cognigy/cognigy-plugin (12 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 754 once invoked, about $0.0005 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.