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 agentmods add skills/agent-sh/agentsys/enhance-docsnpx skills add agent-sh/agentsys --skill enhance-docsgit clone --depth 1 https://github.com/agent-sh/agentsysWhat 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 | $0.00018 | $0.01767 |
| Opus 5 | $0.00009 | $0.00883 |
| Sonnet 5 | $0.00004 | $0.00353 |
| Haiku 4.5 | $0.00002 | $0.00177 |
Grade A, and why
enhance-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
enhance-docs
Analyze documentation for readability, structure, and RAG optimization.
Parse Arguments
const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const targetPath = args.find(a => !a.startsWith('--')) || '.';
const fix = args.includes('--fix');
const aiMode = args.includes('--ai');
Documentation Locations
| Type | Location | Purpose |
|---|---|---|
| User docs | docs/*.md, README.md |
Human-readable guides |
| Agent docs | agent-docs/*.md |
AI reference material |
| Project memory | CLAUDE.md, AGENTS.md |
AI context/instructions |
Optimization Modes
AI-Only Mode (--ai)
For agent-docs and RAG-optimized documentation:
- Aggressive token reduction
- Dense information packing
- Self-contained sections for retrieval
- Optimal chunking boundaries
Both Mode (--both, default)
For user-facing documentation:
- Balance readability with AI-friendliness
- Clear structure for both humans and retrievers
Workflow
- Discover - Find all .md files
- Parse - Extract structure and content
- Check - Run pattern checks based on mode
- Report - Generate markdown output
- Fix - Apply auto-fixes if --fix
Detection Patterns
1. Link Validation (HIGH)
- Broken anchor links (
[text](#missing-anchor)) - Links to non-existent files
- Malformed link syntax
2. Structure Validation (HIGH)
Heading hierarchy:
- No jumps (H1 → H3 without H2)
- Single H1 per document
- Code blocks with language tags
Position-aware content (based on "lost in the middle" research):
- Critical info at START or END of document
- Supporting details in MIDDLE
- Flag important content buried in middle sections
Recommended structure:
1. Overview/Purpose (START - high attention)
2. Quick Start / TL;DR
3. Detailed Content
4. Reference / API
5. Summary / Key Points (END - high attention)
3. Token Efficiency (HIGH - AI Mode)
Token estimation: characters / 4 or words * 1.3
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.
- 3d ago First seen · 299 lines · 18 tokens per session scan A d5af4630cff1
enhance-docs is a skill published in the GitHub repository agent-sh/agentsys (980 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 1,767 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 2026-08-30.
Other skills, from other repositories
aatmf-t12-rag-poisoning
AATMF T12 — RAG & Knowledge Base Manipulation. PoisonedRAG, vector store flood, embedding collision, retrieval-bias attacks.
omh-llm-app-dev
This is a Hermes-native llm-app-dev workflow skill.
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
kb-retriever
面向本地知识库目录的检索和问答助手。核心流程：(1)分层索引导航 (2)遇到PDF/Excel时必须先读取references学习处理方法 (3)处理文件后再检索。按文件类型组合使用 grep、Read、pdfplumber、pandas 进行渐进式检索，避免整文件加载。用户问题涉及"从知识库目录回答问题/检索信息/查资料"时使用。.
byted-bytehouse-hybrid-search
ByteHouse 混合检索 Skill，支持全文检索 + 向量检索，结合 RRF 重排算法实现更精准的检索结果。当用户需要在ByteHouse数据库中进行全文检索 + 向量检索，结合 RRF 重排算法实现更精准的检索结果时，使用此Skill。.
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.