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 docs-lookupgit 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/docs-lookup)<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/docs-lookup"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/docs-lookup.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.01979 |
| Opus 5 | $0.00032 | $0.00989 |
| Sonnet 5 | $0.00013 | $0.00396 |
| Haiku 4.5 | $0.00006 | $0.00198 |
Grade A, and why
docs-lookup 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognigy Docs Lookup
The plugin bundles the official Cognigy documentation MCP server (docs.cognigy.com). Use it as the source of truth for platform questions — the platform changes faster than model training data. Prefer documented answers over prior knowledge, and link the doc page you used.
Default to the filesystem tool, not search. Cognigy's docs pages are very large (parameter-details.mdx alone is 62 KB) and search_cognigy_documentation returns matched pages whole rather than as excerpts, so its payload scales with page size instead of relevance. Measured: a Voice Gateway barge-in query returned 90 KB via search vs ~4 KB via rg; a conceptual "which tool does the AI Agent call" query returned 280 KB via search — exceeding the tool-result limit and yielding nothing usable — vs ~3 KB via rg.
Tools
query_docs_filesystem_cognigy_documentation— the primary tool. Read-only shell-like queries over a virtual filesystem of every docs page (.mdx) plus OpenAPI specs. The server documents support forrg,grep,find,tree,ls,cat,head,tail,stat,wc,sort,uniq,cut,sed,awk,jqand basic text utilities; run--helpon any command to confirm usage. Flag coverage is narrower than GNU (e.g.cat -Ais rejected), so keep flags conventional. These run inside the MCP tool's virtual filesystem — NEVER in the local shell. Each call is stateless: the working directory resets to/, so use absolute paths or chain with&&(cd /api-reference && ls).search_cognigy_documentation— semantic search. Takes only aquerystring: no result limit, no relevance floor, no filters. Fall back to it only when you cannot guess the docs' vocabulary at all. Expect a very large result; when it overflows into a file, triage by extracting theTitle:/Page:lines, then read the best one or two pages with the filesystem tool — never read the dump whole.submit_feedback— report incorrect, outdated, or confusing docs to the Cognigy docs team. Offer this when you and the user hit a genuine documentation gap.
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 · 80 lines · 65 tokens per session scan A 81649ecd194c
docs-lookup is a skill published in the GitHub repository Cognigy/cognigy-plugin (12 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,979 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…