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/maintaingit clone --depth 1 https://github.com/randomittin/heimdallWhat 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 | $0.00040 | $0.00841 |
| Opus 5 | $0.00020 | $0.00420 |
| Sonnet 5 | $0.00008 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
maintain 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain — Automated Bug Detection & Fix Pipeline
Two-phase maintenance: seek then fix.
Usage
/hmd:maintain — run once (seek + fix)
/hmd:maintain seek — only find bugs, raise issues
/hmd:maintain fix — only fix existing issues
/hmd:maintain auto — schedule recurring via /schedule
Connectors — GitHub issues are the DEFAULT trigger
The queue is connector-fed. GitHub issues are the default connector and trigger:
issue_queue already normalizes them into the queue that the fixer drains. Every
other source is an additional connector that files issues into the SAME queue —
they do not replace GitHub issues, they feed alongside them:
- GitHub issues (default) — a human or a bot opens an issue; it is normalized and picked by the loop. This is the primary path.
- k8s / gcloud / Sentry logs (additional) — the seeker pulls logs, finds
errors, and FILES them as issues into the same queue (labeled
bug,seeker). The log-based seeker is one pluggable connector, not the only entry point.
Connectors stay pluggable: adding or removing a log source never orphans the others, and the fixer path downstream is identical regardless of which connector filed the issue.
Phase 1: Seek
Spawn a seeker agent (the log-based connector) to:
- Pull logs from Kubernetes pods (or local logs, docker, cloud)
- Analyze for errors, crashes, anomalies
- Deduplicate by stack trace signature
- File GitHub issues with full context (labeled "bug,seeker") — into the same queue that human-opened GitHub issues land in.
Phase 2: Fix
Spawn a fixer agent to:
- Pick open issues from the queue (default connector:
gh issue list --label bug --state open, normalized byissue_queue). - For each issue (oldest first):
- Create a
heimdall/*fix branch from main - Implement the minimal fix
- Attest (SI-2) — evidence = recorded real exits; a proof-less fix is un-PR-able
- Open the PR ONLY via
bin/heimdall-issue-pr open(routed through the scoped bot token) — the fixer NEVER pushes a branch or opens a PR by hand, NEVER pushes to main, NEVER merges. Autonomy ends at PR-open; a human merges.
- Create a
- Move to next issue
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.
- 2d ago First seen · 81 lines · 40 tokens per session scan A 2d3cd6f71e63
maintain is a command published in the GitHub repository randomittin/heimdall (5 stars, last pushed 12d ago), licensed MIT. It adds 40 tokens to every session and 841 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.
analyze-repo
Analyze an existing repository's structure, conventions, and guardrails.
doctor
Run IJFW health check (files, MCP server, hooks, memory, caps, framing).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.