cognigy-plugin: Skill for Claude Code

.claude/skills/add-client-platform/SKILL.md

add-client-platform is a skill for Claude Code, Codex from Cognigy/cognigy-plugin. It costs 37 tokens per session (2,916 once invoked), scanned C, original, MIT.

A development guide for adding support for another client platform, such as an AI coding tool or integrated development environment, to the Cognigy plugin.

In plain words
What is it for?
Use it when adding a new supported client, checking manifest discovery, wiring installation, preparing releases, and updating documentation.
Why use it?
It helps avoid duplicate work when a platform may already read an existing plugin manifest, and highlights compatibility details such as credential handling and release setup.

Skill for Claude CodeCodex

Written for Claude Code and Codex: Claude Code plugin machinery, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is Cognigy/cognigy-plugin's own configuration. It tells Claude Code and Codex how to work on cognigy-plugin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cognigy-plugin configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Cognigy/cognigy-plugin/main/.claude/skills/add-client-platform/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Cognigy/cognigy-plugin

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for add-client-platform

README.md
[![agentmods](https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/add-client-platform.svg)](https://agentmods.dev/skills/cognigy/cognigy-plugin/add-client-platform)
Your own site
<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/add-client-platform"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/add-client-platform.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,916 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.02916
Opus 5 $0.00018 $0.01458
Sonnet 5 $0.00007 $0.00583
Haiku 4.5 $0.00004 $0.00292

Measured 6d ago against content hash a914b17b4e64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

add-client-platform scanned grade C with 3 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 6d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

**Let the client's CLI own its config.** If the client ships a CLI that writes its own config (`codex mcp add`), drive the CLI and print a paste-able snippet as fallback when the binary isn't on PATH. Only parse and merg

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **User-global config files** (`~/.codex/config.toml`, extension manifests) use `@latest`, because our releases never re-sync a file that lives in the user's home directory.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

**Spawn through `src/install/cliRunner.ts`.** `detectOnPath()` + `runCliTool()` handle the Windows `.cmd` shim quoting. Never call `spawnSync` on a client CLI directly.
.claude/skills/add-client-platform/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a new client platform to the NiCE Cognigy Plugin — a new AI client the plugin can be installed into (Cursor, Windsurf, Zed, Copilot, JetBrains, …). The four existing clients (claude-code, claude-desktop, codex, gemini) are the reference implementations; copy whichever one matches the new client's shape rather than inventing a new pattern.

Before writing anything: check whether it already works

Several clients read each other's manifests. Codex, for example, resolves plugin manifests in the order .codex-plugin/plugin.json.claude-plugin/plugin.json.cursor-plugin/plugin.json, and marketplace manifests as .agents/plugins/marketplace.json.agents/plugins/api_marketplace.json.claude-plugin/marketplace.json.cursor-plugin/marketplace.json. So a new client may already discover the plugin through a fallback path.

Verify against the client's source or official docs, not blog posts, and check specifically:

  1. Does it read an existing manifest of ours as a fallback? If so, what does the fallback lose (presentation fields, credential handling)?
  2. Does it interpolate credential placeholders (${user_config.*} or equivalent)? Most clients do not — see the credential rule below.
  3. Is there a CLI that owns its config file, or must we merge the file ourselves?
  4. How does the client update an installed plugin? See the update rule below — this is the question most easily assumed and most often wrong.

Only the parts a fallback can't cover need new code.

Pick the archetype

Archetype Reference How it works How updates reach the user
Repo-marketplace plugin claude-code, codex Client discovers plugin/.<client>-plugin/plugin.json via a marketplace manifest in this repo. Installer drives the client CLI (marketplace add), user finishes in the client's plugin UI. The client re-checks the repo ref and swaps the cached plugin; the new manifest's engine pin pulls the matching engine. Only works if the ref moves — pin it to main explicitly.
Direct config merge claude-desktop No CLI. Installer reads/merges the client's own MCP config file, preserving every other key, and chmods it 0600 when it holds secrets. Nothing in the client updates. The MCP entry points at the launcher, which pulls @latest each boot.
Packaged extension gemini A build script emits a release asset; installer runs the client's extensions install against the GitHub release. The client's own extension auto-update, if it has one — install with that flag on.
Stage and register antigravity The installer builds a plugin directory itself and writes the client's own registry entries — no client CLI involved, works before the client's first launch. Nothing in the client updates — we staged the files, so we own refreshing them. The launcher re-stages them after an engine bump.
Credentials only other-hosts The client installs the plugin itself (or takes a hand-written MCP entry); the installer writes ~/.cognigy-plugin/config.json and wires nothing. The host owns the version. Say so and stop.

Read the full file on GitHub · 105 lines

Changes

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.

  1. 6d ago First seen · 105 lines · 37 tokens per session scan C a914b17b4e64

Subscribe to this mod's changes

add-client-platform is a skill published in the GitHub repository Cognigy/cognigy-plugin (12 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 2,916 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens