Borrowing it
Nothing to install: this file belongs to sanmak/specops. 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/sanmak/specops/main/.claude/commands/monitor.mdgit clone --depth 1 https://github.com/sanmak/specopsWrote 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/sanmak/specops/monitor)<a href="https://agentmods.dev/commands/sanmak/specops/monitor"><img src="https://agentmods.dev/badge/commands/sanmak/specops/monitor/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/sanmak/specops/monitor"><img src="https://agentmods.dev/badge/commands/sanmak/specops/monitor.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 | $0.01329 |
| Opus 5.5 | $0.00000 | $0.00532 |
| Sonnet 5.5 | $0.00000 | $0.00266 |
| Haiku 4.5 | $0.00000 | $0.00133 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitor GitHub Actions CI status for the current branch. If any workflow fails, diagnose the failure, fix it, commit, push, and re-monitor — up to 3 cycles.
Instructions
Follow these steps precisely. This command assumes a push has already happened (via /push, /ship, or manual git push).
Step 1: Pre-flight checks
Run git status to check the working tree.
If there are uncommitted changes (modified or untracked files), warn the user: "There are uncommitted changes that could interfere with automated fixes. Run /commit first or commit manually." and stop.
Step 2: Identify CI runs
Get the current commit SHA and branch:
git rev-parse HEAD
git rev-parse --abbrev-ref HEAD
List workflow runs for this commit:
gh run list --branch <branch> --commit <sha> --json databaseId,status,conclusion,name,event --limit 20
If no runs are found, wait 10 seconds and retry. Repeat up to 3 times. If still no runs after 3 polls, tell the user: "No CI runs found for commit . CI may not be configured for this branch." and stop.
Step 3: Wait for runs to complete
If any runs have status of in_progress, queued, or pending:
- Tell the user which workflows are still running (list their names and statuses)
- Wait 30 seconds
- Re-fetch the run list with the same
gh run listcommand - Repeat until all runs have
status: completed
Safety: if you have polled more than 30 times (~15 minutes), stop and tell the user: "CI runs are taking too long. Check GitHub Actions manually." and stop.
Step 4: Check results
Examine the conclusion field of each completed run.
If ALL runs have conclusion: success:
- Report to the user: "All CI checks passed!" with a list of the workflow names
- Stop — you are done
If ANY run has conclusion: failure (or cancelled, timed_out):
- Report which workflows failed (list names and conclusions)
- Proceed to Step 5
Step 5: Diagnose failures
For each failed run, fetch the failure logs:
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 · 136 lines · 0 tokens per session scan A 2275e28c8e11
monitor is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,329 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 2026-08-30.
Other commands, from other repositories
devops
You are the DevOps Specialist -- the single authority on version control, CI/CD pipelines, platform operations (GitHub, Azure DevOps, GitLab), infrastructure, deployment, backup, and cleanup. If it touches git, pipelines, or production infrastructure, it's yours.
skill-creator
Create or update an OpenCode skill using the bundled skill-creator workflow.
publish
Publish oh-my-opencode to npm via GitHub Actions workflow.
taskstoissues
A command that turns structured tasks from project design documents into ordered GitHub Issues, written in simplified Chinese.
deploy
Deploy application with pre/post-deploy checks.
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.