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 espennilsen/pi --skill pr-monitorgit clone --depth 1 https://github.com/espennilsen/piWrote 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/espennilsen/pi/pr-monitor)<a href="https://agentmods.dev/skills/espennilsen/pi/pr-monitor"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/pr-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/espennilsen/pi/pr-monitor"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/pr-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.01071 |
| Opus 5 | $0.00064 | $0.00535 |
| Sonnet 5 | $0.00026 | $0.00214 |
| Haiku 4.5 | $0.00013 | $0.00107 |
Grade A, and why
pr-monitor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Monitor Skill
Scan all GitHub-hosted repos in ~/Dev for open pull requests. Flag stale PRs and report status.
Procedure
Step 1: Scan all repos for open PRs
Run this exact command to collect all open PRs:
for dir in ~/Dev/*/; do
if [ -d "$dir/.git" ]; then
remote=$(git -C "$dir" remote get-url origin 2>/dev/null)
if echo "$remote" | grep -q github.com; then
repo=$(echo "$remote" | sed 's/.*github.com[:/]\(.*\)\.git/\1/' | sed 's/.*github.com[:/]\(.*\)/\1/')
prs=$(timeout 30s gh pr list --repo "$repo" --state open --json number,title,createdAt,headRefName,author,isDraft,reviewDecision)
pr_count=$(echo "${prs:-[]}" | jq 'length' 2>/dev/null)
if [ "${pr_count:-0}" -gt 0 ]; then
echo "=== $(basename "$dir") ($repo) ==="
echo "$prs" | jq -r '.[] | " #\(.number) [\(.headRefName)] \(.title) (by \(.author.login), created \(.createdAt[:10]), draft: \(.isDraft), review: \(.reviewDecision // "none"))"'
echo ""
fi
fi
fi
done
Step 2: Calculate PR age
For each PR, calculate age from createdAt to today. Classify as:
- 🟢 Fresh — 0–1 days old
- 🟡 Aging — 2–3 days old
- 🔴 Stale — 4+ days old
Step 3: Format the report
Output a table with columns:
| Repo | PR | Branch | Title | Author | Age | Status | Review |
|---|
Group by repo. Show age badge (🟢/🟡/🔴). Include draft status and review decision.
Step 4: Summary
End with:
- Total open PRs across all repos
- Stale count (4+ days) — these need attention
- Aging count (2–3 days) — these are approaching stale
- Action items — specific PRs that need review or merge
Step 5: Deduplication check (before alerting)
Before sending any Telegram alert, check today's daily memory log for PRs already covered. Optionally, write a lightweight per-PR "alert sent" timestamp (e.g., pr-monitor: [repo] #[number] — <date>) to memory so overlapping executions don't duplicate alerts.
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.
- 13d ago First seen · 105 lines · 129 tokens per session scan A 5b3844354768
pr-monitor is a skill published in the GitHub repository espennilsen/pi (119 stars, last pushed 2d ago), licensed MIT. It adds 129 tokens to every session and 1,071 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
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…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.