discover-a-skill

discover-a-skill is a skill for Claude Code, Codex from avibe-bot/askill. It costs 31 tokens per session (1,186 once invoked), scanned A, original, MIT.

A guide and command workflow for finding, inspecting, installing, running, and updating skills for coding agents.

In plain words
What is it for?
Use it when you need a new agent capability, want to inspect a skill, install one from a registry or repository, run its commands, or troubleshoot updates.
Why use it?
It gives agents a consistent way to discover available capabilities and follow each skill’s instructions instead of guessing how to install or use them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions OpenCode.

Good fit Use it when you need a new agent capability, want to inspect a skill, install one from a registry or repository, run its commands, or troubleshoot updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/avibe-bot/askill/discover-a-skill
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 avibe-bot/askill --skill discover-a-skill
Clone the repo
git clone --depth 1 https://github.com/avibe-bot/askill

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 discover-a-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/avibe-bot/askill/discover-a-skill/github.svg)](https://agentmods.dev/skills/avibe-bot/askill/discover-a-skill)
Your own site
<a href="https://agentmods.dev/skills/avibe-bot/askill/discover-a-skill"><img src="https://agentmods.dev/badge/skills/avibe-bot/askill/discover-a-skill/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 discover-a-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/avibe-bot/askill/discover-a-skill"><img src="https://agentmods.dev/badge/skills/avibe-bot/askill/discover-a-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,186 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 $0.00031 $0.01186
Opus 5 $0.00015 $0.00593
Sonnet 5 $0.00006 $0.00237
Haiku 4.5 $0.00003 $0.00119

Measured 8d ago against content hash 494ff31d2758, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

discover-a-skill 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 8d 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/discover-a-skill/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discover a Skill

Use this skill when you need to operate askill reliably as an AI agent: discover skills, install them, run commands, maintain updates, and troubleshoot install/runtime issues.

Core Workflow

When a user asks for a capability that might be implemented as a skill:

  1. Discover candidates: askill find <query>
  2. Inspect details: askill info <slug>
  3. Install: askill add <source> -y
  4. Read installed instructions: <skill-dir>/SKILL.md
  5. Execute commands if defined: askill run <skill>:<command> [args]

Always prefer reading the installed SKILL.md before improvising.

Source Formats You Should Use

Use any supported install source:

  • @author/skill-name - published skill slug from askill registry
  • owner/repo - discover and install from a GitHub repo
  • owner/repo@skill-name - install one named skill
  • owner/repo/path/to/skill - install by explicit folder path
  • gh:owner/repo@skill-name - explicit GitHub-prefixed format
  • https://github.com/owner/repo - full GitHub URL
  • ./local/path - local skill directory for testing

Notes:

  • askill install, askill add, and askill i are equivalent
  • Prefer explicit, non-interactive calls (-y) in agent workflows

Installation Patterns

Non-interactive (agent-safe)

# Published skill slug
askill add @johndoe/awesome-tool -y

# Indexed GitHub skill slug
askill add gh:owner/repo@skill-name -y

Install all discovered skills from a repo

askill add gh:owner/repo --all -y

Preview before install

askill add gh:owner/repo --list

Target specific agents

askill add gh:owner/repo@skill-name -a claude-code opencode -y

Global install

askill add gh:owner/repo@skill-name -g -y

Copy mode (avoid symlink)

askill add gh:owner/repo@skill-name --copy -y

Where Skills Are Installed

askill installs to canonical directories and links into agent-specific paths.

  • Project canonical: .agents/skills/<skill>/
  • Global canonical: ~/.agents/skills/<skill>/
  • Agent paths: .claude/skills/, .opencode/skills/, .cursor/skills/, etc.

Read the full file on GitHub · 172 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. 8d ago First seen · 172 lines · 31 tokens per session scan A 494ff31d2758

Subscribe to this mod's changes

discover-a-skill is a skill published in the GitHub repository avibe-bot/askill (13 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,186 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 2026-08-30.