drive-me

drive-me is a skill for Claude Code from arch3rPro/ark-space. It costs 103 tokens per session (1,224 once invoked), scanned A, original, MIT.

An execution-coaching tool that turns a vague, stalled, or oversized goal into one bounded next action. It defines the scope, non-goals, completion conditions, and a simple way to check progress.

In plain words
What is it for?
Use it to restart paused work, choose the next task, timebox an effort, set acceptance criteria, or create an accountability check-in.
Why use it?
It removes uncertainty about what to do next when procrastination, scope growth, or repeated planning is blocking progress.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ark-space plugin — 18 skills, 11 agents shipped together

Install

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.

agentmods
npx agentmods add skills/arch3rpro/ark-space/drive-me
Any agent
npx skills add arch3rPro/ark-space --skill drive-me
Clone the repo
git clone --depth 1 https://github.com/arch3rPro/ark-space

Made for: Claude Code.

Or install ark-space, the plugin that ships this one along with the rest of its 18 skills, 11 agents.

Wrote 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.

agentmods badge for drive-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/arch3rpro/ark-space/drive-me.svg)](https://agentmods.dev/skills/arch3rpro/ark-space/drive-me)
Your own site
<a href="https://agentmods.dev/skills/arch3rpro/ark-space/drive-me"><img src="https://agentmods.dev/badge/skills/arch3rpro/ark-space/drive-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,224 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.01224
Opus 5 $0.00051 $0.00612
Sonnet 5 $0.00021 $0.00245
Haiku 4.5 $0.00010 $0.00122

Measured 6d ago against content hash 08e8216ed2de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

drive-me 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 6d 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.

plugins/ark-space/skills/drive-me/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drive-Me

Help the user move from vague intention, avoidance, or scope drift to one safe, bounded action. This is a practical execution-coaching skill, not a motivational speech or long-form planning generator.

When to use this skill

Use this skill when the request shows one or more of these signals:

  • The user is stuck, procrastinating, restarting after a gap, or losing momentum.
  • The user wants to decide what to do next but the goal is vague or too large.
  • The user wants to build something before validating value, users, alternatives, or urgency.
  • The user keeps redesigning the system/process instead of doing the work.
  • The user asks for accountability, a check-in, timeboxing, or anti-procrastination support.
  • The user needs scope, non-goals, acceptance criteria, or a visible progress signal.

Do not use this skill for routine coding tasks, fully specified implementation requests, or broad strategy discussions unless execution friction is the main blocker.

Gather only relevant context

Use the user’s current request as the default source of truth. When they point to a note, task list, project document, calendar, or other context, read it and use it as evidence; those sources are optional inputs, not prerequisites.

If material context is missing, say what is unknown and ask at most one focused question. Do not infer priorities, deadlines, available time, personal limits, or motivation. Do not search for or require a fixed filename.

Treat personal constraints as operating context, not as reasons to shame the user. Do not modify user notes, task systems, files, calendars, or constraints unless the user explicitly asks.

Diagnose the real blocker

Classify the current friction using evidence from the request and any provided context. Prefer the smallest sufficient diagnosis:

  • Unclear value: the idea does not yet state the problem, target user, expected benefit, alternatives, or urgency.
  • Priority conflict: worthwhile work is losing to a more valuable or urgent commitment.
  • Scope drift: the proposed work is broader than the evidence, timebox, or acceptance conditions support.
  • Unclear next action: the goal is known but the first physical, finishable action is missing.
  • Missing feedback loop: progress is invisible, so interest and follow-through decay.
  • Execution environment friction: the task is too hard to start, record, resume, or verify.

Read the full file on GitHub · 99 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago First seen · 99 lines · 103 tokens per session scan A 08e8216ed2de

Subscribe to this mod's changes

drive-me is a skill published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 10d ago), licensed MIT. It adds 103 tokens to every session and 1,224 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

my-adhd-caveman

Self-contained output mode: ADHD actable structure (action first, numbered steps, one next action, one-line progress) plus caveman diction (drop fluff/articles, fragments, fewer tokens). Use when the user says "adhd-caveman", "my-adhd-caveman", or invokes /my-adhd-caveman. Needs no other skills.

SteinsFu/my-adhd-caveman · 83 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens

collaboration-platform-administration

Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal…

cbrock84/headcount · 93 tokens

invest

First-time fork users: run the invest-setup skill first to initialize. The main flow lives in this skill (the AI agent uses the CLI/MCP to view the portfolio / run the committee / replay decision history). The Web GUI has been retired (2026-07) — every capability is exposed via CLI subcommands / MCP tools. The backend…

longsizhuo/openInvest · 261 tokens

invest-backup

Back up / restore openInvest's local state — memory/ (holdings, strategy, user profile, committee records, dream logs) + db/ (trade ledger, job run history, market-data cache) + .env (SMTP/API credentials) + userprofile.json. All of this data is .gitignore'd with no historical versions in git, so a single accidental…

longsizhuo/openInvest · 202 tokens

spike-consumer-adversarial

OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIALID and data path.

testdouble/han · 0 tokens