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 kevinnft/ai-agent-skills --skill ecosystem-tool-evaluationgit clone --depth 1 https://github.com/kevinnft/ai-agent-skillsWrote 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/kevinnft/ai-agent-skills/ecosystem-tool-evaluation)<a href="https://agentmods.dev/skills/kevinnft/ai-agent-skills/ecosystem-tool-evaluation"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/ecosystem-tool-evaluation/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/kevinnft/ai-agent-skills/ecosystem-tool-evaluation"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/ecosystem-tool-evaluation.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 | $0.00046 | $0.03229 |
| Opus 5 | $0.00023 | $0.01614 |
| Sonnet 5 | $0.00009 | $0.00646 |
| Haiku 4.5 | $0.00005 | $0.00323 |
Grade B, and why
ecosystem-tool-evaluation scanned grade B with 1 finding 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 9d 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.
- sudo snap install drawio How it starts
The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ecosystem Tool Evaluation
When users ask to "install all useful tools" or explore an ecosystem, evaluate each tool's complexity vs. benefit BEFORE installing. Avoid leaving tools in "cloned but not configured" states.
Core Principle
Evaluate → Decide → Install (or Skip)
Don't clone/install first and explain complexity later. The user's time and disk space are valuable.
Evaluation Framework
For each tool, assess:
1. Setup Complexity
| Level | Description | Examples | Action |
|---|---|---|---|
| Low | Single command, no dependencies | npm install -g tool, pip install tool |
✅ Install immediately |
| Medium | 2-3 commands, common dependencies | Install app + config file | ✅ Install with brief explanation |
| High | Multiple steps, external services | Docker + database + API keys + integration | ⚠️ Explain complexity, ask before proceeding |
| Very High | Infrastructure setup, ongoing maintenance | Self-hosted services, multi-component systems | ❌ Explain why it's complex, offer alternatives |
2. Immediate Usability
- Ready after install? (✅ tokscale, draw.io) → Install
- Needs configuration? (⚠️ API keys, config files) → Install + configure
- Needs integration? (❌ hindsight → Hermes) → Explain complexity first
3. Value vs. Effort
| Scenario | Setup Time | Value | Decision |
|---|---|---|---|
| High value, low effort | 2-5 min | High | ✅ Install |
| High value, medium effort | 10-15 min | High | ✅ Install with explanation |
| High value, high effort | 30-60 min | High | ⚠️ Ask user first |
| Low value, any effort | Any | Low | ❌ Skip or explain why not worth it |
| Marginal value, high effort | 30+ min | Marginal | ❌ Skip, explain alternative |
User Preference Patterns
For "Gas" Users (Full Automation)
User signal: "gas dan otomatis aktif maksimal dan perfect lalu test pastikan sempurna"
Pattern: User wants FULL AUTOMATION with verification, not step-by-step confirmation.
What ships with it
7 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.
- references/batch-repo-analysis-workflow.md 7.8 KB
- references/external-repo-evaluation.md 7.1 KB
- references/hermes-ecosystem-analysis-pattern.md 4.8 KB
- references/memory-provider-migration.md 8.2 KB
- references/mnemosyne-installation-migration.md 7.1 KB
- references/skill-registry-discovery.md 5.9 KB
- references/ubuntu-2404-pip-workarounds.md 5.4 KB
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.
- 9d ago First seen · 413 lines · 46 tokens per session scan B 811bc7f7ab30
ecosystem-tool-evaluation is a skill published in the GitHub repository kevinnft/ai-agent-skills (14 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 3,229 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
extract-design
Extract a complete design system — colors, typography, spacing, components, shadows, and W3C design tokens — from any live website using Dembrandt. Runs a headless browser against the URL and returns real computed values from the DOM. Use when you need a site's actual design tokens, want to reverse-engineer a visual…
elevation-and-depth
Elevation — subtle shadows and layering — communicates visual hierarchy by lifting elements above the surface. Combined with border-radius, it creates the tactile quality of cards, modals, and interactive surfaces. Use when designing cards, dropdowns, modals, tooltips, or any floating UI element.
loading-states-and-perceived-performance
Manage user expectations during wait times with appropriate loading states — from simple spinners to complex skeleton screens and staggered animations. Perceived performance is often more important than actual load time. Use when designing data-heavy components, handling API calls, building hero sections, or improving…
tab-navigation
Tabs organise related content under a shared context — switching tabs swaps the view without leaving the page. Use when a screen has multiple distinct content areas that share a common header or action set, and when the user needs to switch between them frequently. Use when designing tabbed layouts, content panels…
status-colors-and-errors
Keep status and error colours minimal and consistent — too many semantic colours confuse users. Each colour must mean exactly one thing. Errors should be recoverable, large failures must be prevented, and the UI should always give the user a path forward. Use when designing status indicators, error states, form…