What is autonomous-drive?

A controlled work loop for an autonomous delivery session: read the task ledger, complete one eligible task, run its verification, and decide whether the session must stop.

Use it when starting or resuming a drive session, deciding whether a task can proceed, or closing a completed slice and moving to the next one.

It limits unattended work to clearly tracked tasks and ensures each iteration respects approval, verification, and stop rules.

autonomous-drive — Skill for Claude Code by jeet129

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.

Any agent

npx skills add jeet129/praxis --skill autonomous-drive

Clone the repo

git clone --depth 1 https://github.com/jeet129/praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 105 skills, 12 commands, 17 agents, 6 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jeet129/praxis/autonomous-drive/github.svg)](https://agentmods.dev/skills/jeet129/praxis/autonomous-drive)

Your own site

<a href="https://agentmods.dev/skills/jeet129/praxis/autonomous-drive"><img src="https://agentmods.dev/badge/skills/jeet129/praxis/autonomous-drive/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jeet129/praxis/autonomous-drive"><img src="https://agentmods.dev/badge/skills/jeet129/praxis/autonomous-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 158 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,722 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00158	$0.03722
Opus 5	$0.00079	$0.01861
Sonnet 5	$0.00032	$0.00744
Haiku 4.5	$0.00016	$0.00372

Measured 9d ago against content hash 967645576326, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autonomous-drive 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 9d 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/praxis-codex/skills/autonomous-drive/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Drive

capability: orchestration
domain: cross-cutting
state: experimental
dependencies:
  - using-praxis
  - adaptive-model-routing
  - definition-of-done
triggers:
  - "starting or resuming a drive session"
  - "what does one drive iteration do?"
  - "slice is draining — run the gate reviewers and close it"
  - "deciding whether a stop_flag must be raised this iteration"
  - "cross-slice continuation after a gate close"
outputs:
  - updated task ledger (.project/working/slice-<id>-tasks.yaml)
  - slice-close summary (.project/telemetry/summaries/slice-<id>-summary.md)
  - stop_flags (drive runner contract)
  - model-routing log entries (per task)
consumers:
  - delivery-lead (primary — executes this protocol every drive iteration)
  - scripts/praxis-drive.sh (the unattended runner; enforces caps this SKILL cannot)
references:
  - loop-contracts.md
  - phase-gates.md

One iteration, one task. This SKILL is what the Delivery Lead runs inside a drive session — the autonomy dial (.project/governance/autonomy.yaml when the project carries an override, else the plugin's governance/autonomy.yaml) sets how often a human is consulted; this SKILL is what happens between those touchpoints. No contract, no loop: every claim here traces back to references/loop-contracts.md.

When this SKILL fires

A drive session starts or resumes (/drive, or scripts/praxis-drive.sh invoking the harness with the drive prompt).
The Delivery Lead needs to decide what a single iteration does before exiting.
A slice's tasks are all done and the slice needs to drain through its gates.
A stop_flags decision must be made — is this a decision point, a gate, or genuinely clear to continue?

One iteration = one task

Each drive iteration is a fresh-context invocation with a constant prompt — deliberately constant: identical prefixes are served from the harness prompt cache, keeping fresh contexts cheap. Keep the prompt stable; volatile ledger state lives in the files it reads, never in the prompt. Within it:

Read the full file on GitHub · 209 lines

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.

9d ago First seen · 209 lines · 158 tokens per session scan A 967645576326

Subscribe to this mod's changes

autonomous-drive is a skill published in the GitHub repository jeet129/praxis (7 stars, last pushed 4d ago), licensed MIT. It adds 158 tokens to every session and 3,722 once invoked, about $0.0008 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.

Planning Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

autonomous-drive