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 skills add Cognigy/cognigy-plugin --skill xappsgit 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/xapps)<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/xapps"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/xapps/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/xapps"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/xapps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.03069 |
| Opus 5.5 | $0.00024 | $0.01228 |
| Sonnet 5.5 | $0.00012 | $0.00614 |
| Haiku 4.5 | $0.00006 | $0.00307 |
Grade A, and why
xapps 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 2mo 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xApps
xApps are interactive in-conversation mini-apps: you render an HTML page or an Adaptive
Card to the user, they interact, and their submitted data flows back into the conversation.
xApps are built as flow nodes managed with manage_flow_nodes (extension
@cognigy/basic-nodes).
Two hard rules
xApp: Init Session(initAppSession) must run before any other xApp node. It creates the session and populatesinput.apps.url(session URL) andinput.apps.baseUrl. Every other xApp node depends on a live session. Creating an xApp node without a precedinginitAppSessionin the flow returns a_hints.warning— add Init Session first.- Data comes back via
input/context, not a return value — see "Accessing xApp data".
Where xApp nodes go
Like all manage_flow_nodes nodes, xApp nodes live inside a tool branch — never before
the AI Agent Job node (see the flow-nodes guide). "Init Session at the beginning" means the
beginning of the xApp sequence inside the tool branch, not the flow's absolute start.
Typical chain inside a tool:
tool node ──appendChild──▶ initAppSession
──append──────▶ showXAppAdaptiveCard { waitForInput: true, storeResultInContext: true, contextKey: "result" }
──append──────▶ code / say (reads context.result or input.data._cognigy._app.payload)
▶ Resolve Tool Action
Workflow
1. Create a tool — create_tool { aiAgentId, toolType: 'tool', name: 'Collect Details', config: { toolId: 'collect_details', description: 'Collect details via an xApp' } } → toolNodeId
2. Init the session — manage_flow_nodes { operation: 'create', flowId, parentNodeId: '<toolNodeId>', mode: 'appendChild', nodeType: 'initAppSession', label: 'xApp: Init Session' }
3. Show a UI + wait — manage_flow_nodes { operation: 'create', flowId, parentNodeId: '<initSessionNodeId>', mode: 'append', nodeType: 'showXAppAdaptiveCard', label: 'xApp: Show Card', config: { card: { ... }, waitForInput: true, storeResultInContext: true, contextKey: 'result' } }
4. Use the result — add a code/say node after it that reads context.result or input.data._cognigy._app.payload
5. List nodes — manage_flow_nodes { operation: 'list', flowId }
What ships with it
6 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.
- 2mo ago First seen · 220 lines · 59 tokens per session scan A 53a93ae99260
xapps is a skill published in the GitHub repository Cognigy/cognigy-plugin (18 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 3,069 once invoked, about $0.0002 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.
xapps compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xappsCognigy/cognigy-plugin | Skill | 18 | yesterday | MIT | A | 59 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |