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 chrono-meta/forge-harness --skill pr-review-watchergit clone --depth 1 https://github.com/chrono-meta/forge-harnessWrote 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/chrono-meta/forge-harness/pr-review-watcher)<a href="https://agentmods.dev/skills/chrono-meta/forge-harness/pr-review-watcher"><img src="https://agentmods.dev/badge/skills/chrono-meta/forge-harness/pr-review-watcher/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/chrono-meta/forge-harness/pr-review-watcher"><img src="https://agentmods.dev/badge/skills/chrono-meta/forge-harness/pr-review-watcher.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 | $0.00053 | $0.01309 |
| Opus 5.5 | $0.00021 | $0.00524 |
| Sonnet 5.5 | $0.00011 | $0.00262 |
| Haiku 4.5 | $0.00005 | $0.00131 |
Grade A, and why
pr-review-watcher 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DEPRECATED (2026-05-18): Directly replaceable by
gh pr view --json reviewscall with no real-world usage evidence. For PR review-related functionality, useharness-pr-reviewerskill instead.
pr-review-watcher — PR Review Arrival Monitor + Instant Summary
Monitors in the background while waiting for a PR reviewer, maintaining the Claude Code session. Delivers review summary + approval status + action items all at once when a review arrives.
Triggers
/pr-review-watcher <PR number> # Monitor PR in current repo (default 2-min interval)
/pr-review-watcher <PR number> --repo owner/repo # Specify a particular repo
/pr-review-watcher <PR number> --interval <seconds> # Change polling interval (default 120 seconds)
/pr-review-watcher <PR number> --once # Check current review status only (no monitoring)
Installable independently — works correctly with plugin install only, without full harness clone.
Step 1. Check Current Review Status
gh pr view <PR number> --json title,state,reviewRequests,reviews \
--jq '{title: .title, state: .state, requested: [.reviewRequests[].login], reviews: [.reviews[] | {author: .author.login, state: .state, body: .body}]}'
Output interpretation:
reviewRequests: people with review requested (no response yet)reviews[].state:APPROVED/CHANGES_REQUESTED/COMMENTED/DISMISSED
With --once flag: Report Step 1 results only and exit.
Step 2. Start Background Monitoring
If no reviews yet, run polling loop in background:
until gh pr view <PR number> --repo <repo> --json reviews \
--jq '.reviews | length > 0' 2>/dev/null | grep -q "true"; do
sleep <interval>
done
Report to user:
⏳ Monitoring PR #<N> for reviews (every <interval> seconds)
Reviewers: <requested list>
Will notify automatically when a review arrives.
Step 3. Instant Summary on Review Arrival
Report immediately in the following format when a review is detected:
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 Changed 028e4332b55d
- 1mo ago First seen · 139 lines · 53 tokens per session scan A 3126ceacfd67
pr-review-watcher is a skill published in the GitHub repository chrono-meta/forge-harness (30 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,309 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 2026-09-04.
Other skills, from other repositories
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
steward-prep-delivery
Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check.
effect-ledger
Record an effect, sign an effect, reconcile an effect or check "did this PR merge" through the signed AIWG effect ledger, using one aiwg effect command with scriptable exit codes.
contribute-start
Initialize an AIWG contribution workflow by creating a feature branch, configuring DCO, and linking a tracking issue.
launch
Planning releases and reporting delivery work from GitHub PR history. Use when versioning, CHANGELOGs, rollout or rollback plans, engineering metrics, retrospectives, or stakeholder reports are needed.
project-setup
Add a GitHub repository as a tracked project — creates workspace entity, installs workflow automation missions, and includes in dev brief scope.