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-toolsgit 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-tools)<a href="https://agentmods.dev/skills/matebenyovszky/agentplaybooks/agentplaybooks-tools"><img src="https://agentmods.dev/badge/skills/matebenyovszky/agentplaybooks/agentplaybooks-tools/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-tools"><img src="https://agentmods.dev/badge/skills/matebenyovszky/agentplaybooks/agentplaybooks-tools.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 | $0.00036 | $0.01003 |
| Opus 5.5 | $0.00014 | $0.00401 |
| Sonnet 5 | $0.00007 | $0.00201 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
agentplaybooks-tools 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 yesterday.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentPlaybooks skills and tools in Hermes
Use the AgentPlaybooks CLI (apb) to make a playbook's skills and tools
available to Hermes. Work in the project directory unless the user requests the
global scope. Set HERMES_HOME before running commands when a non-default Hermes
profile is the intended target.
Check the CLI
Run apb --version. If the CLI is missing, explain that Node.js 20+ and
@agentplaybooks/cli must be installed separately. For a remote Hermes
gateway, verify Node.js and apb on the gateway host/container, not just on the
desktop client; the CLI must be able to write the selected gateway profile.
This skill does not install software or run commands by itself.
Connect MCP/OpenAPI tools and install skills
- For private playbooks or hosted management operations, authenticate the CLI
with
apb login. Never ask for an API key in chat. - Preview
apb connect <guid> --target=hermesand explain that it adds the hosted playbook MCP endpoint to the selected Hermes profile. This connection exposes that playbook's MCP tools, including its configured federated MCP/OpenAPI tools. - The plan reports the required environment variable. Ask the user to configure a playbook-scoped API key in the selected Hermes profile's secret environment; do not request or print the value.
- After the user reviews and approves the planned local change, run
apb connect <guid> --target=hermes --apply. - To install private skills locally, separately preview
apb pull <guid> ., then after review runapb pull <guid> . --apply. - Preview
apb sync . --target=hermes. Explain that it registers the pulled skills and merges MCP definitions from the local project into the selected Hermes profile'sconfig.yaml. After review, apply withapb sync . --target=hermes --apply.
Public skills can also be installed directly from the playbook's
/.well-known/skills/ URL. For an account-wide connection, preview
apb connect --account --target=hermes; after review, apply with
apb connect --account --target=hermes --apply.
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.
- yesterday First seen · 83 lines · 36 tokens per session scan A 096514317123
agentplaybooks-tools is a skill published in the GitHub repository matebenyovszky/agentplaybooks (7 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,003 once invoked, about $0.0001 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 2026-09-27.
Other skills, from other repositories
nornweave-api
Give AI agents their own email inboxes using the NornWeave API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, retrieving threads, searching messages, or integrating with email providers (Mailgun, SES, SendGrid, Resend). NornWeave provides LLM-ready markdown parsing and…
umg-mcp-authoring
Use when Codex needs to create, edit, inspect, validate, or demo UE5.8 UMG interfaces through Unreal Motion Graphics MCP/FabUmgMcp, especially target/default workflows, widget tree authoring, HLSL-backed UI materials, Sequencer widget animations, Blueprint event wiring, readback validation, or operation-trace demo…
umg-material-mcp
Use when Codex needs to create, inspect, edit, delete, or validate UE5.8 material assets through Unreal Motion Graphics MCP/FabUmgMcp HLSL material tools, especially one-HLSL Custom-node authoring, UI-default versus non-UI material type selection, union-only writes, semantic outputs, hlsldelete recovery, or Material…
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-agenda
View and manage org-mode agenda, scheduled tasks, TODOs, and deadlines via the org MCP server. Use when the user asks about their schedule, agenda, tasks, or deadlines. Triggers: "show my agenda", "what's on my schedule", "tasks for today", "tomorrow's agenda", "what do I have this week", "show next week", "last…
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"…