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/2ykwang/agent-skills/docsnpx skills add 2ykwang/agent-skills --skill docsgit clone --depth 1 https://github.com/2ykwang/agent-skillsWrote 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/2ykwang/agent-skills/docs)<a href="https://agentmods.dev/skills/2ykwang/agent-skills/docs"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/docs.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.00747 |
| Opus 5 | $0.00042 | $0.00374 |
| Sonnet 5 | $0.00017 | $0.00149 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs
Input
$ARGUMENTS
Instructions
Document Root
Documents managed by this skill are stored under docs/generated/.
They are organized by category subdirectories: docs/generated/<category>/<slug>.md
Documents outside docs/generated/ are considered manually written and must never be modified.
Tool Usage Rules
Always use the tools below for document search and management. Do not open files one by one — search with patterns.
| Purpose | Tool | Usage |
|---|---|---|
| Find document files | Glob | docs/generated/**/*.md pattern to get full document list |
| Search frontmatter | Grep | Filter by title:, category: patterns |
| Read existing docs | Read | Read frontmatter + body (only necessary documents) |
| Verify code references | Glob | Check if file paths in code_refs exist |
| Create documents | Write | Create new document files |
| Update documents | Edit | Update specific parts of existing documents |
| Scan INDEX | Read | Read docs/generated/INDEX.md for category structure and document list |
Subcommand Routing
The first word of $ARGUMENTS determines the subcommand.
| First word | Action |
|---|---|
write |
Read and execute references/write-procedure.md |
check |
Read and execute references/check-procedure.md |
| (none / help) | Print usage below and stop |
When run without a subcommand:
## docs
Writes and maintains project documentation under `docs/generated/`.
### Commands
| Command | Description |
|---------|-------------|
| write <topic> [code-path] | Write or update a document on the topic |
| check | Check all document status (stale, broken refs, orphan docs) |
### Features
- Uses `[symbol](file-path)` reference pointers instead of code blocks
- Organized by category folders under `docs/generated/`
- INDEX.md based document indexing
Argument Parsing
Parse the remaining arguments after removing the subcommand keyword (write / check).
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 90 lines · 83 tokens per session scan A 5d06a1839bb8
docs is a skill published in the GitHub repository 2ykwang/agent-skills (19 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 747 once invoked, about $0.0004 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
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
clawkeeper
Install, configure, verify, and debug the Clawkeeper watcher stack in this workspace. Use when a user asks to set up clawkeeper, initialize remote or local mode, enable clawkeeper-watcher, wire clawkeeper-bands, diagnose context-judge routing, inspect watcher logs, fix mode/config mismatches, or troubleshoot startup…
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
feishu-doc
Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.