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 matebenyovszky/agentplaybooks --skill agentplaybooks-cligit clone --depth 1 https://github.com/matebenyovszky/agentplaybooksWrote 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/matebenyovszky/agentplaybooks/agentplaybooks-cli)<a href="https://agentmods.dev/skills/matebenyovszky/agentplaybooks/agentplaybooks-cli"><img src="https://agentmods.dev/badge/skills/matebenyovszky/agentplaybooks/agentplaybooks-cli/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/matebenyovszky/agentplaybooks/agentplaybooks-cli"><img src="https://agentmods.dev/badge/skills/matebenyovszky/agentplaybooks/agentplaybooks-cli.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 | $0.00106 | $0.00824 |
| Opus 5.5 | $0.00042 | $0.00330 |
| Sonnet 5.5 | $0.00021 | $0.00165 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
agentplaybooks-cli 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 2d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentPlaybooks CLI
The CLI works on files in the user's project and home directory, so it needs a terminal. Run it through npm with the version pinned, which is the version this plugin was released and tested with:
npx --yes @agentplaybooks/[email protected] <command>
In chat or Cowork, where there is no project directory, use the connected AgentPlaybooks tools (see the playbooks skill) instead of this CLI.
Commands
| Command | What it does | Writes? |
|---|---|---|
doctor [path] --json |
Health report: inventory, spec violations, likely hard-coded secrets, insecure MCP URLs, drift between tools, a 0–100 score | Never |
sync [path] --json |
Plan the canonical agentplaybook.json plus the platform files missing from enabled targets |
Plan only |
sync [path] --target=claude,cursor --apply |
Write those targets, with backups under .agentplaybooks/backups/ |
Yes |
playbooks --json |
List the hosted playbooks the stored key can reach | Never |
pull <guid> [path] --json |
Plan restoring a hosted playbook into the project | Plan only |
push [path] --json |
Plan uploading local instructions, skills, and MCP servers, plus a private versioned backup | Plan only |
backups <guid> --json |
List the backups of a hosted playbook | Never |
Every writing command plans first. Run it without --apply, show the user the
plan — files created or merged, conflicts, secret references found — and run
it again with --apply only after the user agrees.
Credentials
doctorandsyncare local and need no account.playbooks,pull,push, andbackupsneed a stored key. If one is missing, the user runsnpx --yes @agentplaybooks/[email protected] loginin their own terminal; it prompts for the key and stores it in the user's private credential file. Never ask for the key in chat, and never print, read, or copy that file.- Against a self-hosted server, add
--url=<server base URL>tologinand to the account commands, or setAGENTPLAYBOOKS_URL. A server whose certificate comes from a private CA also needsNODE_EXTRA_CA_CERTSset to that CA's file in the user's terminal. - Secret values never move. The CLI writes
${VAR}references, anddoctorreports a credential that is hard-coded in a config file without printing it.
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.
- 2d ago Changed 0a2dfa5e15f9
- 5d ago Changed efffed5dfd42
- 6d ago Changed 69954df71f11
- 8d ago Changed · +4 lines 7786c15831a1
- 13d ago Changed 45b0cd98ff13
- 24d ago First seen · 56 lines · 106 tokens per session scan A 0798545a4b55
agentplaybooks-cli is a skill published in the GitHub repository matebenyovszky/agentplaybooks (11 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 824 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
org-update-todo
Update the TODO state and metadata of an existing org-mode heading via the org MCP server. Use when the user wants to change a task's state, priority, tags, or timestamps. Triggers: "mark as done", "complete this task", "reschedule", "change priority", "update the deadline", "close this TODO", "set a deadline", "retag…
org-capture
Create new org-mode headings and notes via the org MCP server. Use when the user wants to add a new task, note, journal entry, or any new heading to their org files. Triggers: "add a task", "create a note", "capture this", "log an entry", "add to my notes", "create a TODO", "add a journal entry", "record this idea"…
org-search
Search and browse org-mode documents via the org MCP server. Use when the user wants to find content across org files, list their org documents, read file contents, or navigate headings and outlines. Triggers: "search my notes for...", "find org pages about...", "list my org files", "show outline of...", "read the…
tmux-via-mcp
Use the tmux MCP tools to create sessions, shape layouts, run tracked commands, and automate interactive terminals when a real TTY or parallel panes are required.
tmux-buffer-explorer
Explore large tmux buffers via search and bounded slices. Use when buffer data is too large to load at once or needs incremental inspection.
ai-first-pastebin
Use 呵.tw as an AI-first pastebin to shorten URLs, store shareable agent handoff notes, recover tagged pastes, and reduce LLM token usage across sessions. Trigger this skill when the user wants to: (1) turn long URLs into short links, (2) park long non-secret intermediate output outside the context window, (3) hand off…