Tailor: Skill for Claude Code

.agents/skills/dependency-governance/SKILL.md

dependency-governance is a skill for Claude Code, Codex from AmanKtyr/Tailor. It costs 36 tokens per session (877 once invoked), scanned A, original, MIT.

A set of rules for reviewing software packages before they are installed or upgraded. A package is reusable code from outside the project; supply-chain security concerns the risks those external packages can introduce.

In plain words
What is it for?
Use it when evaluating, proposing, installing, or upgrading packages across programming ecosystems, including checks for maintenance, licensing, redundancy, and trivial bloat.
Why use it?
It helps avoid unnecessary dependencies, security and maintenance risks, license conflicts, and extra bundle size. It also rejects small packages when the programming language already provides the same operation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is AmanKtyr/Tailor's own configuration. It tells Claude Code and Codex how to work on Tailor 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 Tailor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AmanKtyr/Tailor. 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/AmanKtyr/Tailor/main/.agents/skills/dependency-governance/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AmanKtyr/Tailor

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 dependency-governance

README.md
[![agentmods](https://agentmods.dev/badge/skills/amanktyr/tailor/dependency-governance.svg)](https://agentmods.dev/skills/amanktyr/tailor/dependency-governance)
Your own site
<a href="https://agentmods.dev/skills/amanktyr/tailor/dependency-governance"><img src="https://agentmods.dev/badge/skills/amanktyr/tailor/dependency-governance.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 877 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 $0.00036 $0.00877
Opus 5 $0.00018 $0.00439
Sonnet 5 $0.00007 $0.00175
Haiku 4.5 $0.00004 $0.00088

Measured yesterday against content hash 8c410be47511, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dependency-governance 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 yesterday.

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/skills/dependency-governance/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependency Governance Skill

Activate this skill before installing, proposing, or upgrading any external package (/dependency-check <package> or tailor dependencies --check <package>).

Operational Directive: Every external package is a liability in security, bundle size, and maintenance. Treat additions as exceptional.


1. Automated Rejection Table for Trivial Micro-Packages

Always reject external packages for operations natively supported by standard language primitives:

Proposed Package Recommendation Preferred Native Alternative
is-odd / is-even REJECT (n % 2 !== 0) / (n % 2 === 0)
left-pad / pad REJECT String.prototype.padStart()
is-number / is-string REJECT typeof x === 'number' / typeof x === 'string'
clone-deep / lodash.clonedeep REJECT structuredClone(obj)
deepmerge / object-assign REJECT Object spread { ...a, ...b } or small typed helper
is-promise REJECT Boolean(x && typeof x.then === 'function')
array-flatten REJECT Array.prototype.flat(Infinity)

2. Redundancy & Modern Alternative Checks

Proposed Package Check Existing In Workspace Modern Framework Alternative
axios Check if got, node-fetch, or native fetch exists Native global fetch()
moment Check if date-fns, dayjs, or luxon exists date-fns or Intl.DateTimeFormat
uuid Check if nanoid or cuid exists crypto.randomUUID()
crypto-js Check if native crypto exists node:crypto or Web Crypto API

3. Supply-Chain Security & License Matrix

Before approving any non-trivial package, verify:

  1. Security Vulnerabilities: Run npm audit, pip-audit, or cargo audit.
  2. Maintenance Activity: Confirm active commits and releases within the past 12 months.
  3. License Classification:
    • Permissive (Approved): MIT, Apache-2.0, BSD-2-Clause, BSD-3-Clause, ISC, 0BSD, CC0-1.0.
    • Copyleft (Requires Review): GPL-2.0, GPL-3.0, AGPL-3.0, SSPL, LGPL-3.0.
  4. Documentation: Record confirmed packages in .ai/DEPENDENCIES.md.

Read the full file on GitHub · 63 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. yesterday Changed · +13 lines · +5 tokens per session 8c410be47511
  2. 8d ago First seen · 50 lines · 31 tokens per session scan A 6ee380e20ac0

Subscribe to this mod's changes

dependency-governance is a skill published in the GitHub repository AmanKtyr/Tailor (3 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 877 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.