What is autonomous-lead?

An autonomous software-development workflow that runs without interactive approval steps. It keeps decision logs and creates architecture decision records when a change affects system design.

Executing development tasks autonomously, recording decisions, creating architecture records, and requiring a separate contrarian review before risky implementation.

It preserves a record of autonomous decisions and adds an adversarial review when work is both high-impact and uncertain.

autonomous-lead — Command for Claude Code by adonai-labs/agent-runway

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.

Clone the repo

git clone --depth 1 https://github.com/adonai-labs/agent-runway

Made for: Claude Code.

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/commands/adonai-labs/agent-runway/autonomous-lead/github.svg)](https://agentmods.dev/commands/adonai-labs/agent-runway/autonomous-lead)

Your own site

<a href="https://agentmods.dev/commands/adonai-labs/agent-runway/autonomous-lead"><img src="https://agentmods.dev/badge/commands/adonai-labs/agent-runway/autonomous-lead/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/commands/adonai-labs/agent-runway/autonomous-lead"><img src="https://agentmods.dev/badge/commands/adonai-labs/agent-runway/autonomous-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 153 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.

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	$0.00018	$0.00153
Opus 5.5	$0.00007	$0.00061
Sonnet 5.5	$0.00004	$0.00031
Haiku 4.5	$0.00002	$0.00015

Measured yesterday against content hash 4cda4f517439, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autonomous-lead 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 yesterday.

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.

src/core/commands/autonomous-lead.md · 11 lines

What it actually says

Autonomous Lead

Read and follow the skill at {{skills}}/autonomous-lead/SKILL.md.

Execute autonomously without interactive approval gates, but always persist decision logs in .agent-runway/logs/autonomous-runs/ and create ADRs when architectural impact exists. Apply internal risk scoring and enforce a mandatory contrarian gate for high-impact/high-uncertainty work before implementation starts. When the contrarian gate triggers, delegate to the {{skills}}/contrarian/SKILL.md skill with a completed /contrarian Handoff — do not perform the contrarian review in the same context as implementation.

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.

yesterday Changed · +4 lines · +18 tokens per session 4cda4f517439
2mo ago First seen · 7 lines · 0 tokens per session scan A 9d10f511c5b2

Subscribe to this mod's changes

autonomous-lead is a command published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 153 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 2026-08-31.

Claude Code Code review ai ai-agents architecture cursor

autonomous-lead next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
autonomous-leadadonai-labs/agent-runway	Command	2	2d ago	MIT	A	18	Claude Code
code-diagramusamaijazmughal/code-diagram	Command	2	6mo ago	MIT	A	81	Claude Code, Gemini CLI
arc-auditart9mid/arc-skill	Command	8	6mo ago	none	A	76	Claude Code
refactor-cleanwshobson/agents	Command	42k	yesterday	MIT	A	26	Claude Code
parallel-analyzeCloudAI-X/claude-workflow-v2	Command	1.4k	1mo ago	MIT	A	25	Claude Code
reviewvinvcn/addyosmani-agent-skills-zh	Command	46	17d ago	MIT	A	16	Claude Code
review-codechohra-med/expo_boilerplate	Command	36	1mo ago	MIT	A	50	Claude Code