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 | $0.01365 |
| Opus 5.5 | $0.00014 | $0.00546 |
| Sonnet 5.5 | $0.00007 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00136 |
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 7d 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 — 108 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.
Guided setup
Requires @agentplaybooks/[email protected] or later. Run on the gateway host/container.
Choose the profile explicitly using --profile=<name> and, when needed,
--hermes-home=<installation-directory>; keep that selection on every command.
- Run
apb hermes doctor <guid> . --profile=<name>to report the runtime, destination permissions and credential presence without network calls. - Use
apb loginfor authenticated file downloads. Never request a key in chat. - Preview
apb hermes setup <guid> . --profile=<name>. Explain the listed files: complete skill trees and their bundled resources are restored. Hosted tools use the playbook MCP endpoint. Use--tools-onlyif only a hosted connection is wanted; account login is then unnecessary. - Explain any conflicts and the required playbook-key variable (by default
APBKS_KEY_AGENTPLAYBOOKS). The user configures it in the profile's secret environment. Values never belong in chat or generated configuration. - Once the user has authorized the shown changes, run the same setup with
--apply. Existing authorization covers this step; do not repeatedly ask for approval of the same setup. - Check the result. Apply also probes MCP initialization and tool listing
using this process's environment. Missing credentials can give exit code 2
after files were installed. Report that distinction; do not claim the
connection works until the probe succeeds. After configuring the key and
restarting the profile, run
apb hermes doctor <guid> . --profile=<name> --checkfrom that environment. This check never invokes a remote tool.
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.
- 7d ago Changed · +11 lines a832c4c62267
- 15d ago Changed 835e65937764
- 17d ago Changed 73915468b3cd
- 18d ago Changed · +9 lines f31ffb25f186
- 25d ago Changed · +5 lines bbbe6ea60e4a
- 1mo ago First seen · 83 lines · 36 tokens per session scan A 096514317123
agentplaybooks-tools is a skill published in the GitHub repository matebenyovszky/agentplaybooks (11 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,365 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.
agentplaybooks-tools compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentplaybooks-toolsmatebenyovszky/agentplaybooks | Skill | 11 | 2d ago | MIT | A | 36 | Claude Code, Codex |
| nornweave-apiDataCovey/nornweave | Skill | 30 | 6d ago | Apache-2.0 | A | 77 | Claude Code, Codex |
| org-update-todoszaffarano/org-mcp-server | Skill | 47 | today | MIT | A | 102 | Claude Code |
| org-agendaszaffarano/org-mcp-server | Skill | 47 | today | MIT | A | 120 | Claude Code |
| org-captureszaffarano/org-mcp-server | Skill | 47 | today | MIT | A | 97 | Claude Code |
| novelai-mcp-toolsxinvxueyuan/NovelAI-Image-MCP | Skill | 12 | today | MIT | A | 56 | Claude Code, Codex |
| novelai-workflowsxinvxueyuan/NovelAI-Image-MCP | Skill | 12 | today | MIT | A | 45 | Claude Code, Codex |