Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add matebenyovszky/agentplaybooks/plugin install 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/commands/matebenyovszky/agentplaybooks/connect)<a href="https://agentmods.dev/commands/matebenyovszky/agentplaybooks/connect"><img src="https://agentmods.dev/badge/commands/matebenyovszky/agentplaybooks/connect/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/commands/matebenyovszky/agentplaybooks/connect"><img src="https://agentmods.dev/badge/commands/matebenyovszky/agentplaybooks/connect.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 | $0.00023 | $0.00396 |
| Opus 5 | $0.00012 | $0.00198 |
| Sonnet 5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
connect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Point the agent tool at either a whole AgentPlaybooks account or one or more
hosted playbooks. --account uses the account-management MCP endpoint and a
user API key; GUIDs use the scoped playbook endpoints. A user API key can also
authenticate those scoped endpoints when the account has access.
- Run:
node "${CLAUDE_PLUGIN_ROOT}/bin/agentplaybooks.js" connect $ARGUMENTS --json - Report the plan: the scope, endpoint URL(s), config entry name(s), which files would be
created or merged, and the environment variable the key will be read from.
The key itself is never written to disk — the config carries
${VAR}. - If
keyPresentInEnvironmentis false, say so before applying. A variable set after the agent tool started is invisible to it, and from the inside that looks identical to a rejected key: the connection establishes, no tools appear, and refreshing fails. The user needs to set it and restart the tool. - Conflicts mean the target's config already holds a different definition under that name, or its format cannot represent this one. Do not work around them — report what conflicts and ask which should win.
- Only after the user confirms, run the same command with
--applyand report what was written (backups land in.agentplaybooks/backups/).
For the whole account use connect --account. For several playbooks use a
comma-separated list of GUIDs. A GUID is the last path segment of the MCP URL.
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 Changed · +2 lines · +5 tokens per session c8c5766d7f5a
- 10d ago First seen · 25 lines · 18 tokens per session scan A 4621f7f8d9e9
connect is a command published in the GitHub repository matebenyovszky/agentplaybooks (5 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 396 once invoked, about $0.0001 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 commands, from other repositories
CHANGELOG
Command "CHANGELOG" from bytedance/UI-TARS-desktop, covering 0.4.0 2024-12-10 - add logging, 1.2.29, 1.2.28, 1.2.26 and 1.2.25.
TODO
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.