autonomize

A command for setting or viewing an autonomy agreement for the current task. It defines how much effort to spend, when to stop and when to ask the user before making a choice.

In plain words
What is it for?
Use it to choose an effort level, stopping rule and asking policy, or to review and adjust the active agreement.
Why use it?
It makes the agent's working limits explicit instead of leaving effort, stopping points and questions ambiguous.

Command

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 commands/ackeskin/contexture/autonomize
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 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 $0.00048 $0.00279
Opus 5 $0.00024 $0.00139
Sonnet 5 $0.00010 $0.00056
Haiku 4.5 $0.00005 $0.00028

Measured 2d ago against content hash 6a33b2673b02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autonomize 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 2d 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.

commands/autonomize.md · 18 lines

What it actually says

Run the autonomize skill for the current context.

Forms:

  • /autonomize — with a contract set, show the active contract + its source tier and offer to edit; with none set, run the short contract-establishing interview.
  • /autonomize effort=thorough stopping=criteria-met ask=forks-only — kickoff: propose those values, confirm, write the task contract. No interview.
  • /autonomize <natural-language steer> — e.g. "leave it here", "go deeper", "keep pushing": map to a contract delta, propose-confirm, apply for the current task only.

effort ∈ minimal | balanced | thorough | exhaustive · stopping ∈ criteria-met | diminishing-returns | budget | user-anytime · ask ∈ forks-only | every-step | until-blocked.

A live steer is task-scoped and never persists. Every write passes propose-confirm; the skill never auto-fires.

See ~/.claude/skills/autonomize/SKILL.md for the full contract model and precedence.

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. 2d ago First seen · 18 lines · 48 tokens per session scan A 6a33b2673b02

Subscribe to this mod's changes

autonomize is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 279 once invoked, about $0.0002 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.