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 llaa33219/casabot --skill subskillsgit clone --depth 1 https://github.com/llaa33219/casabotWrote 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/llaa33219/casabot/subskills)<a href="https://agentmods.dev/skills/llaa33219/casabot/subskills"><img src="https://agentmods.dev/badge/skills/llaa33219/casabot/subskills/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/llaa33219/casabot/subskills"><img src="https://agentmods.dev/badge/skills/llaa33219/casabot/subskills.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 | $0.00018 | $0.01244 |
| Opus 5 | $0.00009 | $0.00622 |
| Sonnet 5 | $0.00004 | $0.00249 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade C, and why
Sub-Agent Skills (subskills) scanned grade C 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/casabot/skills/<skill>/subskills/<subskill-name> How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-Agent Skills (subskills)
This manual explains the /subskills directory mechanism — a way to attach, discover, and manage skill documents that sub-agents can use.
1. What is /subskills?
Each skill directory under ~/casabot/skills/ can contain a /subskills subdirectory. This subdirectory holds skill documents intended for sub-agents rather than the base agent.
~/casabot/skills/
├── agent/
│ ├── SKILL.md
│ └── subskills/ ← Skills for sub-agents in this domain
│ ├── python-dev/
│ │ └── SKILL.md
│ └── web-scraper/
│ └── SKILL.md
├── memory/
│ ├── SKILL.md
│ └── subskills/
│ └── vector-search/
│ └── SKILL.md
└── subskills/
└── SKILL.md ← This document
Key Concepts
- Base skills (
SKILL.mdat the skill root) are read by the base agent. - Subskills (
subskills/<name>/SKILL.md) are passed to sub-agents when they are created or delegated tasks. - Subskill documents follow the same format as regular skills (YAML frontmatter + Markdown body).
2. Who can add subskills?
Agent-driven discovery
The base agent (or a sub-agent) can search for relevant tools, libraries, or techniques and write a new subskill document based on the findings.
# Create a subskill directory
mkdir -p ~/casabot/skills/agent/subskills/python-dev
# Write the subskill document
cat > ~/casabot/skills/agent/subskills/python-dev/SKILL.md << 'EOF'
---
name: Python Development
description: Guidelines and tools for Python-based sub-agents
metadata:
casabot:
requires:
bins: [python3, pip]
---
# Python Development
Instructions for sub-agents working on Python projects...
EOF
User-provided subskills
Users can also place skill documents directly into the /subskills directory of any skill. This is useful for domain-specific instructions or custom tool configurations that the user wants sub-agents to follow.
# User manually adds a subskill
mkdir -p ~/casabot/skills/agent/subskills/my-custom-tool
cat > ~/casabot/skills/agent/subskills/my-custom-tool/SKILL.md << 'EOF'
---
name: My Custom Tool
description: Custom tool usage instructions for sub-agents
metadata:
casabot:
requires:
bins: []
---
# My Custom Tool
(Custom instructions for sub-agents...)
EOF
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 · 200 lines · 18 tokens per session scan C 4ebce2dbab0a
Sub-Agent Skills (subskills) is a skill published in the GitHub repository llaa33219/casabot (5 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,244 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…