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.
npx agentmods add commands/randomittin/heimdall/maintain-checkgit 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/maintain-check)<a href="https://agentmods.dev/commands/randomittin/heimdall/maintain-check"><img src="https://agentmods.dev/badge/commands/randomittin/heimdall/maintain-check.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.02147 |
| Opus 5 | $0.00017 | $0.01073 |
| Sonnet 5 | $0.00007 | $0.00429 |
| Haiku 4.5 | $0.00003 | $0.00215 |
Grade A, and why
maintain-check 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 4d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainer Check Cycle
Run a single maintainer autopilot cycle. This is the command /loop or /schedule
calls repeatedly. The heavy lifting is NOT prose LLM steps — it is delegated to the
deterministic engine bin/heimdall-maintain-loop, which wraps the honest issue loop
(bin/heimdall-issue-loop → pick → orient → fix → GATE → attest → PR). The engine
owns the parts that must never drift: the token BUDGET CAP, the run-away STOP
conditions, the approval PARK, agent-pool BACKPRESSURE, and the machine-readable
CHECKPOINT receipt that lets a fresh session resume after death/compaction.
Your job here is thin: gate on enablement, run ONE cycle (or preview it), and report the receipt. Do not re-implement scan/triage/fix in prose — the engine is authoritative.
Pre-flight
- Check maintainer is enabled:
heimdall-state get '.maintainer.enabled'
If false, respond: "Maintainer mode is off. Run /hmd:maintain to enable." and stop.
- Check the ⚠-class queue has not aged. Every ⚠ observation owes, within 24h of being filed, either a fix or a durable triage reason a human wrote:
heimdall-sla --repo . # exit 1 on BREACH; each breach names id, class, age
A BREACH is not a blocker for this cycle — it is work this cycle owes. Fold every breached item into the triage below, oldest first, and give each one a verdict. The reason this runs here rather than nowhere: the aging IS the bug. An unactioned item that quietly gets older is the same disease as a monitor that quietly stops — in both cases the absence of a signal is indistinguishable from the absence of a problem, so some surface has to ask the question on a schedule.
Dry-Run Mode
If $ARGUMENTS contains --dry-run, DO NOT execute or mutate anything. Show the plan:
# What the next drain WOULD do — budget snapshot + queued issues in pick order +
# the action each would take (park for approval vs fix+gate+PR). Mutates nothing.
heimdall-maintain-loop plan --repo .
# The current queue buckets + in-flight machine states (read-only).
heimdall-issue-loop status --repo .
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.
- 4d ago First seen · 179 lines · 34 tokens per session scan A 65ff0f61f3c8
maintain-check is a command published in the GitHub repository randomittin/heimdall (5 stars, last pushed 13d ago), licensed MIT. It adds 34 tokens to every session and 2,147 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.
Other commands, from other repositories
autocode
Fully autonomous development pipeline. Give it a feature description or PRD file and it will plan, write tests, implement code, run tests, and verify — all automatically with zero human intervention.
autocode-new
Scan current project and generate a project-specific autocode development pipeline (agents, commands, rules, hooks). Interactive setup wizard.
go-review
Go code review for idiomatic patterns.
save
Save this conversation as a new or existing reusable context.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
test
Run all PandaFilter verification steps in order. Stop and report on first failure. This is the required pre-commit gate.