Borrowing it
Nothing to install: this file belongs to virtengine/bosun. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/virtengine/bosun/main/.github/prompts/bosun-monitor-continue.prompt.mdgit clone --depth 1 https://github.com/virtengine/bosunWrote 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/virtengine/bosun/bosun-monitor-continue)<a href="https://agentmods.dev/commands/virtengine/bosun/bosun-monitor-continue"><img src="https://agentmods.dev/badge/commands/virtengine/bosun/bosun-monitor-continue/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/virtengine/bosun/bosun-monitor-continue"><img src="https://agentmods.dev/badge/commands/virtengine/bosun/bosun-monitor-continue.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 | $0.00033 | $0.00703 |
| Opus 5.5 | $0.00013 | $0.00281 |
| Sonnet 5.5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
Continue Bosun Monitor 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
Resume the Bosun local operations monitor for this workspace in continuous mode.
Mandatory behavior:
- Read the latest three
.bosun-monitor/session*.mdnotes before touching runtime state. - Rebuild the open-blocker list from the newest note and continue from the narrowest unresolved blocker.
- Confirm the global
bosunnpm link points atD:/source/repos/virtengine-gh/bosun; runnpm linkfrom this repo first if it still points at an older checkout. - Resume with
bosun simulate task <task-id>,bosun simulate task restart, orbosun simulate taskbefore using the full daemon as the main monitor path. - Re-check simulator progress first. Only re-check daemon health, active paths, live task progress, workflow-run behavior, and recent non-monitor throughput after the simulator proves a real task can complete end to end or when you need minimal comparison evidence for the blocker.
- Inspect at least one real task path end to end before declaring health, including task execution, PR creation, review, fixes if review finds issues, and merge.
- If the previous cycle changed code and validation is incomplete, finish simulator validation before new cleanup.
- If the previous cycle only did runtime cleanup, keep going until you either land a durable source fix or isolate a precise blocker with proof.
- If the same blocker family appeared in the previous two notes, stop replaying long simulator runs and convert the evidence into the smallest deterministic test or harness before another reset/retry.
- Before trusting a rerun after source edits, prove whether the simulator loaded the source checkout, workspace mirror, task worktree, or a cached long-lived runtime. Restart or isolate the minimal runtime path if the loaded code may be stale.
- Only repair missing dependencies or generated outputs once per symptom family. A repeat is an incident to diagnose, not another cleanup step.
- Do not unlock full-daemon monitoring until the simulator confirms that a real task finishes properly end to end and the merge lands cleanly.
- Once the simulator gate is satisfied, run the daemon and continue optimizing the live system in parallel.
- End by writing a fresh handoff note for the next cycle and reporting
healthy,warning, orincidentexactly as the agent requires.
Treat any user-supplied text as a priority hint, not as a replacement for the required startup sequence.
Continue the Bosun local ops monitor. Read the latest three session notes first, rebuild the open-blocker list, and resume from the narrowest unresolved blocker in simulator-first mode. Do not switch to full-daemon monitoring until bosun simulate task proves that a real task completes implementation, push, PR creation, review, fixes if needed, and merge end to end. After that gate is satisfied, run the daemon and keep optimizing live throughput in parallel. Do not stop at runtime cleanup or repeated replay. If a blocker repeats, prove runtime lineage and add or run deterministic coverage for the seam before another long simulator loop. Land the smallest durable source fix you can, or leave a precise symptom -> proof -> code path -> blocker handoff for the next cycle.
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 · 29 lines · 33 tokens per session scan A df5e5baf6a65
Continue Bosun Monitor is a command published in the GitHub repository virtengine/bosun (284 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 703 once invoked, about $0.0001 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 2026-09-19.
Other commands, from other repositories
type-coverage
Vérification Couverture des Types Python.
debug
Diagnose Ansible playbook issues from symptoms.
AGENTS
Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.
optimization
Performance optimization through specialized analysis.
pre-edit
Execute pre-edit validations and agent assignment before file modifications.
debugger
Systematic debugging with TodoWrite and Memory integration.