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.
git clone --depth 1 https://github.com/randomittin/heimdallWrote 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.
[](https://agentmods.dev/commands/randomittin/heimdall/autonomy)<a href="https://agentmods.dev/commands/randomittin/heimdall/autonomy"><img src="https://agentmods.dev/badge/commands/randomittin/heimdall/autonomy/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.
<a href="https://agentmods.dev/commands/randomittin/heimdall/autonomy"><img src="https://agentmods.dev/badge/commands/randomittin/heimdall/autonomy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00050 | $0.00615 |
| Opus 5.5 | $0.00020 | $0.00246 |
| Sonnet 5.5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
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 1mo 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.
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:
-
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.
- If empty or missing: Show current setting from
-
Update the state file (the on-disk key stays
.project.autonomy_level— do not rename it):
heimdall-state set '.project.autonomy_level' '<new_level>'
-
Confirm with a compact status line:
◀ 1 Guided/◀ 2 Checkpoint ▶/3 Full Auto ▶- Show the active setting highlighted, with arrows indicating cycle direction
-
If changing from a lower to higher setting, add: "More autonomous now.
/hmd:autonomy -to step back." -
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:levelstill works as a deprecated alias for one release, but/hmd:autonomyis the name going forward.
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.
- 1mo ago First seen · 48 lines · 50 tokens per session scan A 02764302e205
autonomy is a command published in the GitHub repository randomittin/heimdall (5 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 615 once invoked, about $0.0002 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.
Other commands, from other repositories
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
atomic-plan
Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
documentation
Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.