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.
git clone --depth 1 https://github.com/Cognigy/cognigy-pluginWrote 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.
[](https://agentmods.dev/agents/cognigy/cognigy-plugin/cognigy-agent-builder)<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>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 | $0.00096 | $0.00754 |
| Opus 5 | $0.00048 | $0.00377 |
| Sonnet 5 | $0.00019 | $0.00151 |
| Haiku 4.5 | $0.00010 | $0.00075 |
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.
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
- List projects.
list_resources { resourceType: "project" }. Decide the target project (ask the caller if ambiguous). For a brand-new project, create the agent first withprojectIdomitted, then continue the LLM checks against the returnedprojectId. - 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-emptyconnectionId. - 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_exportable→exportthelargeLanguageModel+ itsconnection→upload_and_inspect→import→ verify withlist_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-projectconnectionId.
- Check the target project:
- 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. - 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. - Refine.
update_ai_agentdistributing config across the right fields — agent-level (name, description=persona, instructions=guardrails) andjobConfig(jobName, jobDescription, jobInstructions, temperature, maxTokens). Do not dump everything intodescription. - Iterate steps 4–5 until the behavior matches the request.
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.
- 8d ago First seen · 29 lines · 96 tokens per session scan A 070ec7ffcf66
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.