agentmods.dev

evaluate-dependency

evaluate-dependency is a skill for Claude Code from 686f6c61/alfred-dev. It costs 37 tokens per session (404 once invoked), scanned A, original, MIT.

A Spanish-language procedure for assessing a new software dependency before adding it to a project. It checks the exact version, license, maintenance, security advisories, bundle impact, and related packages.

In plain words
What is it for?
Use it to audit npm, pip, Cargo, or other packages, compare lighter or built-in alternatives, record approval conditions, and identify known CVEs or other risks.
Why use it?
It records an evidence-based decision in docs/project/dependencies.md and prevents installation when the verdict is not approval. A dependency is an external package that project code relies on.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the alfred-dev plugin — 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server shipped together

not rated 105repo +11 2mo ago A scan SkillSpector: pass 37 tokens original MIT

Good fit Use it to audit npm, pip, Cargo, or other packages, compare lighter or built-in alternatives, record approval conditions, and identify known CVEs or other risks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/686f6c61/alfred-dev/evaluate-dependency
View source ↗ 686f6c61/alfred-dev alfred-dev.com
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.

Any agent
npx skills add 686f6c61/alfred-dev --skill evaluate-dependency
Clone the repo
git clone --depth 1 https://github.com/686f6c61/alfred-dev

Made for: Claude Code.

Or install alfred-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 10 agents, 5 hooks, 1 MCP server.

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 evaluate-dependency

README.md
[![agentmods](https://agentmods.dev/badge/skills/686f6c61/alfred-dev/evaluate-dependency/github.svg)](https://agentmods.dev/skills/686f6c61/alfred-dev/evaluate-dependency)
Your own site
<a href="https://agentmods.dev/skills/686f6c61/alfred-dev/evaluate-dependency"><img src="https://agentmods.dev/badge/skills/686f6c61/alfred-dev/evaluate-dependency/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 evaluate-dependency

Your own site · 80×15
<a href="https://agentmods.dev/skills/686f6c61/alfred-dev/evaluate-dependency"><img src="https://agentmods.dev/badge/skills/686f6c61/alfred-dev/evaluate-dependency.svg" alt="Reviewed on agentmods" width="80" 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 404 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00404
Opus 5.5 $0.00015 $0.00162
Sonnet 5.5 $0.00007 $0.00081
Haiku 4.5 $0.00004 $0.00040

Measured 2mo ago against content hash 77b219d87a55, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evaluate-dependency 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.

skills/evaluate-dependency/SKILL.md · 47 lines

What it actually says

Evaluar una dependencia

Resumen

Antes de añadir un paquete, evalúalo y deja el veredicto en docs/project/dependencies.md. El helper puede crear el esqueleto; tú escribes la fila.

Proceso

  1. Confirma que el paquete no está ya en el registro.

  2. Recoge datos verificables (lockfile, registro, advisory):

    • nombre y versión exacta
    • peso aproximado o impacto en el bundle
    • último release y mantenimiento
    • licencia y compatibilidad con el proyecto
    • CVEs conocidos o «ninguno encontrado» (con fuente)
    • número de transitivas
    • alternativa más ligera o nativa

  3. Veredicto: APROBAR, RECHAZAR o APROBAR CON CONDICIONES.

  4. Añade o actualiza una fila en docs/project/dependencies.md. Si el fichero era esqueleto y ya hay una evaluación real, sustituye <!-- alfred-doc:scaffold --> por <!-- alfred-doc:filled -->.

  5. Si el veredicto no es APROBAR, no la instales. Propón alternativa.

Criterios de éxito

  • La fila existe con versión, licencia y veredicto.
  • Un CVE «no aplica» lleva una frase técnica, no un supuesto.
  • El registro vive en el repo, no solo en el chat.

Qué NO hacer

  • No evalues de memoria sin mirar el lockfile o el manifiesto.
  • No apruebes una dependencia para «ya la usamos todos» sin dato.
  • No dejes licencias como desconocidas sin decirlo.
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. 2mo ago First seen · 47 lines · 37 tokens per session scan A 77b219d87a55

Subscribe to this mod's changes

evaluate-dependency is a skill published in the GitHub repository 686f6c61/alfred-dev (105 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 404 once invoked, about $0.0001 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 2026-08-30.

Claude CodeLegal and complianceSecurityai-agentsautomationclaude-code-pluginsdlc
Related

evaluate-dependency compared with skills from other repositories

evaluate-dependency next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
evaluate-dependency686f6c61/alfred-devSkill1052mo agoMITA37Claude Code
plagiarism-checkerbitwize-music-studio/claude-ai-music-skillsSkill6312d agoCC0-1.0A35Claude Code
employment-compliancecbrock84/headcountSkill2.6k19d agoMITA87Claude Code
performance-managementcbrock84/headcountSkill2.6k19d agoMITA59Claude Code
revenue-recognitioncbrock84/headcountSkill2.6k19d agoMITA69Claude Code
privacy-and-data-protectioncbrock84/headcountSkill2.6k19d agoMITA86Claude Code
benefits-and-leavecbrock84/headcountSkill2.6k19d agoMITA68Claude Code