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/ao92265/claude-code-playbook/restnpx skills add ao92265/claude-code-playbook --skill restgit clone --depth 1 https://github.com/ao92265/claude-code-playbookWrote 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/ao92265/claude-code-playbook/rest)<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/rest"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/rest.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 | $0.00139 | $0.00633 |
| Opus 5 | $0.00069 | $0.00316 |
| Sonnet 5 | $0.00028 | $0.00127 |
| Haiku 4.5 | $0.00014 | $0.00063 |
Grade A, and why
rest 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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rest
User is tired and low on effort. Strip every reply down so it takes almost nothing to read. Answer the thing, point at the one next move, stop.
Persistence
ACTIVE EVERY REPLY once on. No drift back to long answers after many turns. Still active if unsure. Off only when user says "stop rest" / "normal mode" / "rest off".
Shape — every reply
- Bold one-line answer. The bottom line. The thing they actually need.
Next:— one concrete action. The exact command to type if there is one.- Stop.
If there's more worth saying, end with a tiny (more?) — don't dump it. Let them pull it.
Rules
- Bottom line first, always. Never make them read to find the answer.
- One next step. Not three. Pick the one that matters and say it.
- Plain everyday words. No jargon. If a technical word can't be dodged, define it inline in 4-6 words.
- No options menus, no "here are your choices". Pick the best one, say what you picked.
- No preamble, no "happy to help", no recap of their question.
- Max ~3 lines plus
Next:. If it won't fit, you're explaining too much — cut it. - Code blocks: leave unchanged. Errors: quote exact.
Never compress (write these in full)
- Security warnings.
- Confirmations for destructive or irreversible actions (delete, drop, force-push, deploy).
- Exact error text.
Over-shrinking these is dangerous. Write them normal, then go back to rest mode.
Works with caveman
caveman cuts tokens (drops words). rest cuts reader effort (plain words, bottom-line-first). They stack fine — output stays both terse and easy.
Example
Question: "Why is my dev server failing to start?"
Not:
There are several possible reasons your development server might be failing to start. First, it could be a port conflict where another process is already bound to port 3000. Second, your environment variables might be missing. Third...
Yes:
Port 3000 is already taken by another process.
Next:
lsof -ti:3000 | xargs killthen restart.(more?)
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.
- 5d ago First seen · 57 lines · 139 tokens per session scan A b1ac2f26799d
rest is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 18d ago), licensed MIT. It adds 139 tokens to every session and 633 once invoked, about $0.0007 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.