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 skills add vergil-project/vergil-claude-plugin --skill pr-watchgit clone --depth 1 https://github.com/vergil-project/vergil-claude-pluginWrote 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/vergil-project/vergil-claude-plugin/pr-watch)<a href="https://agentmods.dev/skills/vergil-project/vergil-claude-plugin/pr-watch"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/pr-watch/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/vergil-project/vergil-claude-plugin/pr-watch"><img src="https://agentmods.dev/badge/skills/vergil-project/vergil-claude-plugin/pr-watch.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 | $0.01068 |
| Opus 5 | $0.00000 | $0.00534 |
| Sonnet 5 | $0.00000 | $0.00214 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
pr-watch 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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR watch
Drive the post-PR loop. vrg-submit-pr prints /vergil:pr-watch <PR_URL>; run
it in the USER agent session to monitor the open PR through CI and human review,
reconcile feedback, and tell the human when the PR is ready to merge.
vrg-pr-await is a blocking wait — run it in the foreground, don't poll
The loop is driven by vrg-pr-await, which blocks until the PR state
changes (a new commit, a new review, or a check result) and then prints the
current state as JSON. It is a single blocking call — not something to background
or poll around:
- Run one
vrg-pr-await, then wait for it to return. CI and reviews can take minutes; that wait is the call doing its job. Do not background it (&/run_in_background), do notsleep-and-retry, and do not poll GitHub separately in a loop. - It returns once per state change. Act on what it returns (reconcile), push
your commit, then call
vrg-pr-awaitagain with updated--since-*flags. The blocking call is the loop's clock — do not start other work while it waits.
(This is about correctly consuming the blocking vrg-pr-await call — not the
retired continuous-oversight framing; sub-agents remain fine elsewhere.)
Preflight
This skill runs in the USER agent session. Confirm with
vrg-whoami --mode (user). If human, stop — this skill is for the agent.
Monitor & reconcile
Loop:
-
Wait for the PR to settle:
vrg-pr-await <PR_URL> --since-sha <last-head-sha> --since-reviews <last-review-count>(Omit the
--since-*flags on the first call.) It prints PR state as JSON — parse the checks, reviews, and head SHA. -
Stop condition: all required checks are green → tell the human the PR is mergeable. Done.
-
Otherwise reconcile both sources: failing CI checks + human review comments. Patch the code,
vrg-commit, and push (vrg-git push). The new commit re-triggers CI.- Base-branch conflicts are routine here. If the base (
develop) advanced and the PR now conflicts, rebase onto it and force-push — no human sign-off needed:vrg-git fetch origin,vrg-git rebase origin/develop(resolve, validate green), thenvrg-git push --force-with-lease. Force-pushing your own in-flight PR after a rebase is pre-authorized; see Resolving conflicts with the base branch inissue-implement.
- Base-branch conflicts are routine here. If the base (
-
If you cannot get a check green or cannot satisfy a comment, stop and ask the human rather than thrashing.
-
Loop with the updated
--since-sha/--since-reviews.
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.
- 9d ago First seen · 83 lines · 0 tokens per session scan A 4b538d797ab3
pr-watch is a skill published in the GitHub repository vergil-project/vergil-claude-plugin (2 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,068 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 2026-08-31.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.