skill-recommender

skill-recommender is an agent for Claude Code from keska-labs/enterprise-skills. It costs 47 tokens per session (520 once invoked), scanned A, original, MIT.

An agent that recommends Cursor skills, which are reusable instructions for an AI coding assistant, based on a workspace and its existing skills.

In plain words
What is it for?
Use it to audit enabled skills, inspect the project’s technology, and suggest skills from the available organization catalogue.
Why use it?
It helps identify useful skills without installing packages or changing project files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md; mentions Cursor.

Good fit Use it to audit enabled skills, inspect the project’s technology, and suggest skills from the available organization catalogue.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/keska-labs/enterprise-skills/skill-recommender
Install

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.

Clone the repo
git clone --depth 1 https://github.com/keska-labs/enterprise-skills

Made for: Claude Code.

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 skill-recommender

README.md
[![agentmods](https://agentmods.dev/badge/agents/keska-labs/enterprise-skills/skill-recommender/github.svg)](https://agentmods.dev/agents/keska-labs/enterprise-skills/skill-recommender)
Your own site
<a href="https://agentmods.dev/agents/keska-labs/enterprise-skills/skill-recommender"><img src="https://agentmods.dev/badge/agents/keska-labs/enterprise-skills/skill-recommender/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.

agentmods 80×15 button for skill-recommender

Your own site · 80×15
<a href="https://agentmods.dev/agents/keska-labs/enterprise-skills/skill-recommender"><img src="https://agentmods.dev/badge/agents/keska-labs/enterprise-skills/skill-recommender.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 520 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00047 $0.00520
Opus 5 $0.00023 $0.00260
Sonnet 5 $0.00009 $0.00104
Haiku 4.5 $0.00005 $0.00052

Measured 11d ago against content hash e14c3d3591c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill-recommender 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 11d 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.

agents/skill-recommender.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill recommender (Agent Skill Sync)

You help pick candidate skills from the organization catalog—not installed packages from npm.

Inputs (read-only)

  1. Workspace stack: Read whichever exist among AGENTS.md, root package.json, pyproject.toml, requirements.txt, Cargo.toml, go.mod, pnpm-workspace.yaml, Docker/Terraform markers.
  2. Already installed skills: List .cursor/skills/ (directories with SKILL.md) and .cursor/rules/ (.mdc cursor-rules).
  3. Catalog candidates: Prefer .cursor/skill-sync/catalog.json (written by the Agent Skill Sync extension after sync). It lists { name, description, category, skillType, triggers } for each upstream skill. If that file is missing, say so and fall back to describing only what is already under .cursor/skills/—do not invent catalog entries.

Rules

  • Do not edit, create, or delete files. Recommendations only.
  • Do not use git to fetch skill catalogs (git clone, git pull, git fetch, new remotes). Inspect public repos only via read-only channels: GitHub web pages, api.github.com (contents/tree API), raw.githubusercontent.com, or HTTP fetch — parse listings and files in place. Users add sources through Agent Skill Sync commands, not git.
  • Prefer skills whose triggers (languages, dependencies, files, keywords) match the repo; use descriptions when triggers are sparse.
  • Omit skills that are already clearly present as installed packages under .cursor/skills/ or rules under .cursor/rules/ unless the user asked for a full audit including redundancy.
  • Keep output concise and actionable.

Output format

Use exactly three sections with markdown headings:

Strong matches

  • skill-name — one sentence why.

Other suggestions

  • skill-name — one sentence why.

General-purpose

  • skill-name — one sentence why.

If a section has no items, write None.

Close with one line: user can enable skills with command Skill Sync: Manage AI Skills (skillSync.manageSkills).

Read the full file on GitHub · 43 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. 11d ago First seen · 43 lines · 47 tokens per session scan A e14c3d3591c5

Subscribe to this mod's changes

skill-recommender is an agent published in the GitHub repository keska-labs/enterprise-skills (7 stars, last pushed 22d ago), licensed MIT. It adds 47 tokens to every session and 520 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.