Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cboone/agent-harness-plugins/plugin install monitor-prWrote 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/skills/cboone/agent-harness-plugins/monitor)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/monitor"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/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/skills/cboone/agent-harness-plugins/monitor"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/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 | $0.00061 | $0.16763 |
| Opus 5.5 | $0.00024 | $0.06705 |
| Sonnet 5.5 | $0.00012 | $0.03353 |
| Haiku 4.5 | $0.00006 | $0.01676 |
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 3d 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 — 613 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitor PR
Watch a pull request until it is ready to merge, fixing what can be fixed and pausing for what cannot, then offer the merge and bring the base branch and the repository's other sessions up to date once it lands.
This skill starts where pr stops. It is not a passive observer: it repairs failing checks, syncs a stale branch, and drives Copilot feedback to resolution. It is also not a continue-at-all-costs skill. When a decision is genuinely the user's, it stops and asks.
Options
The user may provide these options inline:
<pr-number>: Monitor a specific PR instead of the current branch's PR (e.g.,/monitor-pr:monitor 361)- --interval
<duration>: Override adaptive pacing with a fixed wait (e.g.,--interval 10m) - --ticks
<n|unlimited>: Limit foreground polling, including scheduler fallbacks, tonticks before producing a resumable checkpoint. The default is 3;unlimitedkeeps the foreground turn active until a terminal condition or escalation - --rounds
<n|unlimited>: Change the Copilot round budget from its default of 10.--rounds unlimitedcommits to running until the PR is genuinely clean, however many rounds that takes, and never pauses to ask for more - --triage-after
<n|never>: From Copilot roundn + 1, defer Medium and Low findings to follow-up issues instead of fixing them, per step 7c. The default is 5;neverlets every finding block - --confirm-clean: Require two consecutive clean Copilot reviews rather than one. After the first clean review, request another explicitly and wait for it
- --no-fix: Observe and report only. Never push, never invoke a fixing skill, never request a review, and never merge or act on a merge
Ready Criteria
The repair loop ends when all four axes are clean at the same time, and step 8 takes over. Partial greenness is not readiness.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 613 lines · 61 tokens per session scan A b9c6a0425c53
monitor is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 16,763 once invoked, about $0.0002 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 2026-10-13.
Other skills, from other repositories
review-preflight
Review tooling for a PR: review-preflight prints REVIEW.md's criteria and the PR's live gate state before a review; ci-triage maps a PR's failing checks to already-filed issues.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
review-pr
Comprehensive PR review -- full branch diff against base, commit-by-commit analysis, breaking change detection, conventional commit verification.
pr-audit
Audit a specified PR or PR-ready branch for submission or post-revision readiness. Bind the exact base/head, review commits and net changes, run safe project checks and inspect applicable CI. An audit alone does not authorize fixes, history changes or publication.
git-review
Review code changes, pull requests, or merge requests for bugs, code quality, security, and maintainability. Use when asked to review a PR, MR, diff, or set of changes. Also handles GitHub PRs and GitLab MRs.