level

A deprecated command alias for changing the coding agent's autonomy level. The three levels are Guided, Checkpoint, and Full Auto, and the command now points users to the newer autonomy command.

In plain words
What is it for?
Use it to view or change the project's autonomy setting, although new usage should use the autonomy command.
Why use it?
Existing workflows may still use the old command name after it was renamed. Keeping the alias avoids breaking those workflows while directing users to the replacement.

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/level
Clone the repo
git clone --depth 1 https://github.com/randomittin/heimdall
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 503 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 $0.00044 $0.00503
Opus 5 $0.00022 $0.00251
Sonnet 5 $0.00009 $0.00101
Haiku 4.5 $0.00004 $0.00050

Measured yesterday against content hash 08ba904fa2ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

level 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.

commands/level.md · 39 lines

What it actually says

Set Autonomy (deprecated alias of /hmd:autonomy)

/hmd:level was renamed to /hmd:autonomy. This alias still works for one release so muscle memory doesn't break; it will be removed a couple of releases later.

Instructions:

  1. First, print exactly this one-line notice: '/hmd:level' is now '/hmd:autonomy' — same behavior. Please switch.

  2. Then behave identically to /hmd:autonomy $ARGUMENTS. Parse $ARGUMENTS:

    • If empty or missing: Show current setting from heimdall-state get '.project.autonomy_level' and the descriptions below. 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.
  3. 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

Valid settings:

  • 1 (Guided): Asks before every action.
  • 2 (Checkpoint): Runs on its own, pauses at major milestones.
  • 3 (Full Auto): Runs until complete; only stops if blocked.

Going forward, use /hmd:autonomy (and /hmd:autonomy + / - to cycle).

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. yesterday First seen · 39 lines · 44 tokens per session scan A 08ba904fa2ed

Subscribe to this mod's changes

level is a command published in the GitHub repository randomittin/heimdall (5 stars, last pushed 11d ago), licensed MIT. It adds 44 tokens to every session and 503 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.