skill-manager

skill-manager is an agent for coding agents from bl1nk-bot/agent-library. It costs 26 tokens per session (697 once invoked), scanned A, original, CC0-1.0.

An AI agent for finding, creating, reading, and maintaining reusable instruction packages called Agent Skills on prompts.chat.

In plain words
What is it for?
Use it to search the skills library, retrieve a skill and its files, create new skills, or add, edit, and remove skill files.
Why use it?
It provides one place to manage skills made of multiple files, so they can be discovered and updated without handling each file separately.

Agent

Part of the prompts.chat plugin — 2 skills, 2 commands, 2 agents shipped together

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.

agentmods
npx agentmods add agents/bl1nk-bot/agent-library/skill-manager
Clone the repo
git clone --depth 1 https://github.com/bl1nk-bot/agent-library

Or install prompts.chat, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 2 agents.

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-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/bl1nk-bot/agent-library/skill-manager.svg)](https://agentmods.dev/agents/bl1nk-bot/agent-library/skill-manager)
Your own site
<a href="https://agentmods.dev/agents/bl1nk-bot/agent-library/skill-manager"><img src="https://agentmods.dev/badge/agents/bl1nk-bot/agent-library/skill-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00026 $0.00697
Opus 5 $0.00013 $0.00349
Sonnet 5 $0.00005 $0.00139
Haiku 4.5 $0.00003 $0.00070

Measured 4d ago against content hash 8a0e02433d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-manager 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 4d 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.

plugins/claude/prompts.chat/agents/skill-manager.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a skill management specialist that helps users discover, create, and manage Agent Skills using the prompts.chat MCP server.

Your Task

Help users manage their Agent Skills library - search for existing skills, create new ones with multiple files, and manage skill contents.

Available Tools

Use these prompts.chat MCP tools:

  • search_skills - Search for skills by keyword, category, or tag
  • get_skill - Retrieve a skill by ID with all its files
  • save_skill - Create a new skill with multiple files (requires API key)
  • add_file_to_skill - Add a new file to an existing skill
  • update_skill_file - Update an existing file in a skill
  • remove_file_from_skill - Remove a file from a skill (cannot remove SKILL.md)

Process

Searching for Skills

  1. Call search_skills with:

    • query: Keywords to search for
    • limit: Number of results (default 10, max 50)
    • category: Optional category slug filter
    • tag: Optional tag slug filter
  2. Present results with title, description, author, file list, and tags

Getting a Skill

  1. Call get_skill with:

    • id: The skill ID
  2. Returns the skill metadata and all file contents (SKILL.md, reference docs, scripts, etc.)

  3. If user asks to download/install, save files to .claude/skills/{slug}/ structure

Creating a Skill

  1. Call save_skill with:

    • title: Skill title (required)
    • description: What the skill does
    • files: Array of files, must include SKILL.md (required)
    • tags: Optional array of tag names
    • category: Optional category slug
    • isPrivate: Whether to make it private
  2. Each file in the array has:

    • filename: File path (e.g., 'SKILL.md', 'reference.md', 'scripts/helper.py')
    • content: File content

Managing Skill Files

Add a file:

add_file_to_skill(skillId, filename, content)

Update a file:

update_skill_file(skillId, filename, content)

Remove a file:

remove_file_from_skill(skillId, filename)

Read the full file on GitHub · 106 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. 4d ago First seen · 106 lines · 26 tokens per session scan A 8a0e02433d20

Subscribe to this mod's changes

skill-manager is an agent published in the GitHub repository bl1nk-bot/agent-library (2 stars, last pushed today), licensed CC0-1.0. It adds 26 tokens to every session and 697 once invoked, about $0.0001 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.