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/dream)<a href="https://agentmods.dev/commands/randomittin/heimdall/dream"><img src="https://agentmods.dev/badge/commands/randomittin/heimdall/dream/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/dream"><img src="https://agentmods.dev/badge/commands/randomittin/heimdall/dream.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 | $0.00000 | $0.01914 |
| Opus 5.5 | $0.00000 | $0.00766 |
| Sonnet 5.5 | $0.00000 | $0.00383 |
| Haiku 4.5 | $0.00000 | $0.00191 |
Grade A, and why
dream 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dream — sleep on it, wake to a report
/dream is Heimdall's OVERNIGHT self-improvement + maintainer pass. It does the deep
work while you're away and leaves a morning report (a dream journal) to review —
it does not auto-apply risky changes. Think of it as "sleep on the codebase and
tell me what you learned." (There is no /sleep command — /dream is the canonical
name. The underlying capability stays available as /hmd:self-improve.)
The heavy lifting is delegated to the deterministic orchestrator bin/heimdall-dream,
which REUSES the existing pieces — it invents no new keep/rollback logic:
- autoresearch / self-improve (
bin/heimdall-self-improve) — form routing/planning hypotheses from real metrics + queue evidence, and TEST them with the falsifiable keep-or-rollback gate. An improvement persists ONLY on a measured delta over baseline. - maintainer sweep (seeker) — raise issues found (recurring dead-reason clusters + the live issue queue) WITH proposed fixes, as candidates for a human.
Invariants (never weakened)
- Shadow-first — routing/planning suggestions are SURFACED for morning review, not auto-applied. Only the self-improve keep-gate (safe, measured, reversible) may persist a change overnight; everything else is a suggestion.
- Agent-never-pushes —
/dreamruns nogit push, nogh pr, no merge. It writes a local report; you review and apply in the morning. - Real, not fabricated — every line of the report is sourced from actual self-improve
output + real queue state. With NO evidence yet (empty
metrics.jsonl) the report says "Nothing to suggest" honestly rather than inventing work.
Run it
On-demand (runs the loop now, writes today's report):
# surface-only (default) — shadow-first: suggest routing changes, don't apply them.
heimdall-dream --repo . run --json
# also START one bounded, reversible experiment (safe per the keep-gate: unvalidated,
# snapshotted, auto-rolled-back next cycle if it does not beat baseline):
heimdall-dream --repo . run --overnight --start-experiment --json
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.
- 5d ago Changed e5bb2182fb25
- 8d ago Changed 43360932748e
- 1mo ago First seen · 151 lines · 0 tokens per session scan A 514575e6f807
dream is a command published in the GitHub repository randomittin/heimdall (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,914 tokens. 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
subagent-diagnose
Multi-agent failure-investigation orchestrator. Parallel to /subagent-implementation — same scratchpad + investigator + builder/surgeon + reviewer + FOLLOWUPS pattern — but starts from a failure, not a spec. Two modes share one loop: ci (failed CI run is the brief seed) and bug (freeform symptom paragraph is the brief…
deslop
Audit a standing codebase for accumulated slop — comment noise, AI-tell doc prose, speculative abstraction, reinvented stdlib, duplicate helpers, dead code, swallowed errors, convention drift. Fans out read-only auditors sharded by wiki domain and writes an indexed report into a scratchpad for you to read. /deslop…
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.
implement
Implement in the main agent, with atomic-reviewer gating every checkpoint. For work whose context is already in this conversation, where a fresh subagent would have to re-read what you have already read. Same checkpoints, commit-per-green, and finalize as /subagent-implementation; you write the code.
quick-fix
Implement→review subagent loop with no planning phase, for a fix whose cause is known and whose shape is obvious, however many files it touches. No spec, no worktree, no docs or signals at the end; one audit. Routes to /subagent-diagnose on an unknown cause and to /atomic-plan on an open approach or contract choice.
simplify-analyze
Analyze code for simplification opportunities. Part of simplify- family.