Borrowing it
Nothing to install: this file belongs to Cognigy/cognigy-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Cognigy/cognigy-plugin/main/.claude/skills/add-tool/SKILL.mdgit 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/add-tool)<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/add-tool"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/add-tool/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.
<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/add-tool"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/add-tool.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.01920 |
| Opus 5.5 | $0.00010 | $0.00768 |
| Sonnet 5.5 | $0.00005 | $0.00384 |
| Haiku 4.5 | $0.00003 | $0.00192 |
Grade A, and why
add-tool 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 14d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a new MCP tool (or extend an existing one) in the NiCE Cognigy Plugin's MCP server. The user will describe the tool's purpose, operations, and Cognigy API endpoints it should call.
Skills come first. The plugin's user-facing surface is its skills — each describes a workflow and auto-loads on intent. Tools are the execution primitives a skill orchestrates. Work skill-first: figure out which workflow the capability belongs to, then add or extend a tool only where that workflow needs it. There is no one-skill-per-tool rule — many tools can serve a single workflow, and a new tool usually just slots into an existing skill.
Context
This is a TypeScript MCP server. Tools follow a strict pattern across these files:
| File | Role |
|---|---|
src/tools/definitions.ts |
Tool metadata: name, description, annotations, inputSchema (JSON Schema) |
src/schemas/tools.ts |
Zod validation schemas — one per tool or discriminated union per multi-op tool |
src/tools/handlers.ts |
ToolHandlers class — one handleXxx(args) method per tool + a case in handleToolCall() |
plugin/skills/<name>/SKILL.md |
Hand-authored plugin skill for the tool (auto-loads on intent in supporting clients, e.g. Claude Code) |
src/__tests__/schemas.test.ts |
Schema validation tests |
src/__tests__/tools.test.ts |
Handler tests with mocked CognigyApiClient |
Design philosophy: few tools, many operations
This server deliberately uses few tools (~16) to cover many Cognigy API endpoints (~115). Each tool groups related endpoints under a single operation parameter that acts as a router.
Example: manage_knowledge — one tool covers ~8 endpoints:
create_store→POST /v2.0/knowledgestorescreate_source→POST /v2.0/knowledgestores/{id}/sourceslist_sources→GET /v2.0/knowledgestores/{id}/sourcesingest_source→POST /v2.0/knowledgestores/{id}/sources/{id}/ingestlist_chunks→GET /v2.0/knowledgestores/{id}/chunks- etc.
Why this pattern:
- Fewer tools for the LLM to choose from — 16 tools is much easier for Claude to reason about than 115 separate ones. Less confusion, better tool selection.
- Grouped by domain — each tool maps to a Cognigy domain concept (knowledge, packages, webchat, flow nodes), making it intuitive.
- Shared context — operations within a tool share parameters (like
projectId) and the description explains the full workflow across operations in one place.
What ships with it
3 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.
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.
- 14d ago Changed · +2 lines 8c4a8eacad23
- 2mo ago First seen · 132 lines · 25 tokens per session scan A aa0cb8192072
add-tool is a skill published in the GitHub repository Cognigy/cognigy-plugin (18 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,920 once invoked, about $0.0001 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.
add-tool compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| add-toolCognigy/cognigy-plugin | Skill | 18 | yesterday | MIT | A | 25 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |