autonomy

Ein Befehl zum Festlegen, wie selbstständig Heimdall arbeiten darf. Es gibt drei Stufen: einzelne Freigaben, Pausen an wichtigen Punkten oder vollständiges selbstständiges Ausführen.

In plain words
What is it for?
Für das Anzeigen, Erhöhen, Verringern oder direkte Setzen der Autonomiestufe von Heimdall.
Why use it?
Du kannst bestimmen, wie oft der Agent dich vor weiteren Aktionen einbezieht. Das passt den Ablauf an deinen gewünschten Grad an Kontrolle an.

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/randomittin/heimdall/autonomy
Clone the repo
git clone --depth 1 https://github.com/randomittin/heimdall
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 615 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 $0.00050 $0.00615
Opus 5 $0.00025 $0.00308
Sonnet 5 $0.00010 $0.00123
Haiku 4.5 $0.00005 $0.00061

Measured 2d ago against content hash 02764302e205, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autonomy 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/autonomy.md · 48 lines

What it actually says

Set Autonomy

Set how much Heimdall does on its own before pausing for you.

Valid settings:

  • 1 (Guided): Asks before every action. You approve each step. Nothing runs unreviewed.
  • 2 (Checkpoint): Runs on its own, pausing at major milestones for a look before continuing.
  • 3 (Full Auto): Runs until the work is complete; only stops if blocked or a gate fails.

Instructions:

  1. Parse $ARGUMENTS:

    • If empty or missing: Show current setting from heimdall-state get '.project.autonomy_level' and the descriptions above. Done.
    • If +: Read current setting, increment by 1 (wrap 3→1). Use the result as the new setting.
    • If -: Read current setting, decrement by 1 (wrap 1→3). Use the result as the new setting.
    • If 1, 2, or 3: Use directly as the new setting.
    • If anything else: Show valid options and ask the user to choose.
  2. Update the state file (the on-disk key stays .project.autonomy_level — do not rename it):

heimdall-state set '.project.autonomy_level' '<new_level>'
  1. Confirm with a compact status line:

    • ◀ 1 Guided / ◀ 2 Checkpoint ▶ / 3 Full Auto ▶
    • Show the active setting highlighted, with arrows indicating cycle direction
  2. If changing from a lower to higher setting, add: "More autonomous now. /hmd:autonomy - to step back."

  3. If changing from a higher to lower setting, add: "More checkpoints now. /hmd:autonomy + to step up."

Quick cycling

Since Claude Code keybindings only support built-in actions (no custom action registration), the fastest way to cycle is:

  • /hmd:autonomy + — next setting (1→2→3→1)
  • /hmd:autonomy - — previous setting (3→2→1→3)

This is the Heimdall equivalent of the effort slider. Users can type /a + tab-complete to /hmd:autonomy and then + or -.

/hmd:level still works as a deprecated alias for one release, but /hmd:autonomy is the name going forward.

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 · 48 lines · 50 tokens per session scan A 02764302e205

Subscribe to this mod's changes

autonomy is a command published in the GitHub repository randomittin/heimdall (5 stars, last pushed 11d ago), licensed MIT. It adds 50 tokens to every session and 615 once invoked, about $0.0003 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.