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 playbooksgit 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/playbooks)<a href="https://agentmods.dev/skills/matebenyovszky/agentplaybooks/playbooks"><img src="https://agentmods.dev/badge/skills/matebenyovszky/agentplaybooks/playbooks/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/playbooks"><img src="https://agentmods.dev/badge/skills/matebenyovszky/agentplaybooks/playbooks.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 | $0.00103 | $0.01245 |
| Opus 5.5 | $0.00041 | $0.00498 |
| Sonnet 5.5 | $0.00021 | $0.00249 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
playbooks 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playbooks
A playbook is a portable agent setup the user keeps on AgentPlaybooks: one persona (who the agent is), project instructions (the always-on rules), skills, memory, canvas documents, connected MCP/OpenAPI tools, and a secret vault. The same playbook follows the user into Claude, Cursor, Codex, Hermes, and other clients, so what you write into it is visible there too — and to anyone the playbook is shared with.
The plugin has two connections with the same tools:
- agentplaybooks-account reaches agentplaybooks.ai and signs in with OAuth. It works in every Claude app.
- agentplaybooks-servers runs on the user's machine, in Claude Code, and
reaches every AgentPlaybooks server the user has logged in to with the CLI —
the hosted one, their organisation's own, or several. With more than one,
list_playbooksmarks each playbook'sserver, a playbook tool goes to the server that has itsplaybook_id, andcreate_playbookneedsserver.
Through either, one connection reaches every playbook the account owns or has
been given, and each playbook tool takes a playbook_id (its UUID or GUID).
Use whichever has tools; when both reach a playbook, either works. If neither
has tools, nothing is signed in yet. In a Claude app, ask the user to open the
AgentPlaybooks connector and select Connect. In Claude Code, /mcp shows
each connection's state; a server is added by running the CLI's
login --url=<server> in the user's own terminal and reconnecting
agentplaybooks-servers from /mcp (see the agentplaybooks-cli skill).
Start of a task
list_playbooksto see what exists. Pick by name with the user if more than one fits; do not guess between similar names. A project the CLI has linked to a playbook names it in.agentplaybooks/remote.json; prefer that one.get_playbookfor the chosen one. It returns the persona, instructions, skills, connected servers, and a memory summary.- If the user wants Claude to be that playbook, follow its persona and instructions for the rest of the conversation. Say that you are doing so.
get_memory_contextpacks the memory that matters into one read. Prefer it over reading keys one by one.
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 · +15 lines 1260dbca4b2c
- 18d ago First seen · 82 lines · 103 tokens per session scan A 784958212931
playbooks is a skill published in the GitHub repository matebenyovszky/agentplaybooks (10 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 1,245 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
memai-maintenance
Orchestrator of the MemAI MAINTENANCE pass (long-term agent memory). Runs [[memai-checkpoints]], [[memai-distill]], [[memai-confidence]] and [[memai-link]] as one curation pass, owns what none of them covers — the DOMAIN TREE (nested paths, cross-listing, casing), the DIAGRAMS and the store's DECAY (reviewafter) — and…
memai-confidence
Verify a MemAI memory's claims against live facts and set its confidence (unverified | confirmed | contradicted). Checks the anchors a scan already extracted — file:line, symbol, table/column, domain, URL — against today's source, promotes or demotes each memory, stages a reword for a detail that drifted, and pushes…
memai-checkpoints
The lifecycle of MemAI CHECKPOINTS: deciding which bearing is still current and which one is superseded, archiving the checkpoint of work that is closed or an intra-session trail that a newer one already covers, keeping the single bearing a live effort still needs, correcting a fact in a kept checkpoint that has gone…
memai-distill
Distill and MOVE knowledge between MemAI types: pull what is durable out of one checkpoint (or several) into a note/reasoning/antipattern, change a memory's type (checkpoint→note when the content is timeless), and merge near-duplicates. Use when the user asks to "distill memory", "turn a checkpoint into a note", "move…
memai-link
Stitch the MemAI relations GRAPH: typed edges between memories (supersedes / relatesto / contradicts / linksto), turning [[wikilinks]] written in a body into real edges, connecting complementary memories that share a domain, and preserving lineage (checkpoint to note, archived to successor). Uses dedupscan to find…
memai-memory
How to use the MemAI MCP server (long-term agent memory: one ACID SQLite store, BM25 keyword search) — which tool family to call when: pulse/mustread/search/recall/listbydomain/listrecent/ listdomains/getmemory to read; note, reasoning, antipattern, checkpoint, task, diagram to write…