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.
npx agentmods add skills/cognigy/cognigy-plugin/tools-setupnpx skills add Cognigy/cognigy-plugin --skill tools-setupgit 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/skills/cognigy/cognigy-plugin/tools-setup)<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/tools-setup"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/tools-setup.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 | $0.00036 | $0.03326 |
| Opus 5 | $0.00018 | $0.01663 |
| Sonnet 5 | $0.00007 | $0.00665 |
| Haiku 4.5 | $0.00004 | $0.00333 |
Grade A, and why
tools-setup 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 today.
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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding Tools to an AI Agent
What are tools?
Tools give an AI Agent capabilities beyond conversation — calling APIs, executing code, or searching knowledge bases. Without tools, an agent can only chat.
Steps
- Create the agent first: create_ai_agent { projectId, name, description } (create_tool requires an agent with an auto-provisioned flow)
- create_tool { aiAgentId, toolType, name, config }
- The tool is automatically wired into the agent's flow
- Test with talk_to_agent
Rule of thumb: each tool in an agent flow should have a unique toolId. If you need more logic, parameters, validation, or HTTP calls for that tool, add them inside the same tool branch instead of creating another tool with the same toolId.
Parameter schema rules (config.parameters)
parameters is a JSON Schema string that Cognigy passes VERBATIM to the LLM provider. create_tool / update_tool validate it and reject violations, because a broken schema either fails every conversation turn with a provider 400 (strict models) or is silently dropped (the tool is called with no arguments). The contract:
- Top level:
{"type":"object","properties":{...},"required":[...]}—requiredis mandatory (use[]if nothing is required). - EVERY property needs
"type"AND"description". Allowed types:string,number,integer,boolean,object,array,null. arrayproperties need"items". Nested objects with"properties"also need their own"required"."additionalProperties": falseis injected automatically at every object level.- Strict-mode models (OpenAI Responses API, e.g. gpt-5.x, where strict is forced on): list EVERY property key in
required; make a parameter optional with a nullable type —{"type":["string","null"],"description":"..."}. Non-strict providers ignore this, so it is the safe default. - Nested object properties and
integerare valid at runtime but not renderable by the Cognigy UI's graphical parameter builder — the node's Parameters section then shows the raw JSON editor. That is cosmetic; prefer flat schemas when you don't need nesting.
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.
- today Changed · +11 lines c60f2f6e5e12
- 4d ago First seen · 298 lines · 36 tokens per session scan A 710f6e9b0210
tools-setup is a skill published in the GitHub repository Cognigy/cognigy-plugin (12 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 3,326 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…