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 agentproto/ts --skill drive-agentsgit clone --depth 1 https://github.com/agentproto/tsWrote 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/agentproto/ts/drive-agents)<a href="https://agentmods.dev/skills/agentproto/ts/drive-agents"><img src="https://agentmods.dev/badge/skills/agentproto/ts/drive-agents/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/agentproto/ts/drive-agents"><img src="https://agentmods.dev/badge/skills/agentproto/ts/drive-agents.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 | $0.00081 | $0.00408 |
| Opus 5.5 | $0.00032 | $0.00163 |
| Sonnet 5.5 | $0.00016 | $0.00082 |
| Haiku 4.5 | $0.00008 | $0.00041 |
Grade A, and why
drive-agents 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 1mo 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
drive-agents
Route every step of spawn → prompt → read → wait → lifecycle here. Each row names the primitive that owns the mechanics; open it for tool signatures and recipes.
| I want to… | Open |
|---|---|
| Spawn a session for an agent CLI | ap-spawn-agent |
| Send a follow-up prompt or queue work | ap-prompt-agent |
| See what an agent did so far | ap-read-output |
| Wait for it / them to finish, blocking my turn | ap-wait-fanin |
| Wait without blocking, notified later | ap-wait-durable |
| Kill, archive, restart, or GC sessions | ap-lifecycle |
| Gate its completion before calling it done | ap-policies |
| Run a one-shot shell command | ap-run-command |
| Drive an interactive TUI | ap-terminal |
End-to-end instead of piecemeal?
- One agent, briefed and verified start-to-finish →
pb-new-agent-session. - Several agents in parallel with fan-in →
pb-supervise-parallel-mission.
Start here if you are unsure which primitive you need: pick the row matching the verb in your goal — spawn, prompt, read, wait, kill, gate, run, terminal — and open that skill.
Golden rule: never wait with a shell sleep-poll loop — use session_monitor or
agentproto sessions wait only; a killed poll loop corrupts sessions.
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.
- 1mo ago First seen · 35 lines · 81 tokens per session scan A e1a5bdb213d2
drive-agents is a skill published in the GitHub repository agentproto/ts (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 81 tokens to every session and 408 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).
llm-wiki
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…
extract-wisdom
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).