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 petergaultney/lemonaid --skill watch-prgit clone --depth 1 https://github.com/petergaultney/lemonaidWrote 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/petergaultney/lemonaid/watch-pr)<a href="https://agentmods.dev/skills/petergaultney/lemonaid/watch-pr"><img src="https://agentmods.dev/badge/skills/petergaultney/lemonaid/watch-pr/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/petergaultney/lemonaid/watch-pr"><img src="https://agentmods.dev/badge/skills/petergaultney/lemonaid/watch-pr.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 | $0.00095 | $0.01803 |
| Opus 5.5 | $0.00038 | $0.00721 |
| Sonnet 5.5 | $0.00019 | $0.00361 |
| Haiku 4.5 | $0.00010 | $0.00180 |
Grade A, and why
watch-pr 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 today.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch a PR for pushes, state changes, review comments, conflicts, and failed CI
Arguments
A PR number or URL. If omitted, infer it from the current branch (gh pr view --json number).
--comments --me "<your signature>": also wake on new comments from anyone but you, and, as the PR's author, when it starts conflicting with its base or its CI fails. Use it on every PR you open.<your signature>is the one you sign Relay Comments with, e.g.Author (MotorHoe).--legacy <name>: another signature whose comments count as yours, e.g. one you signed with before (repeatable).- Without
--comments: pushes, merge/close, draft/ready, and review decision only, e.g. when you reviewed someone else's PR. Conflicts and CI are the author's to fix, so a reviewer isn't woken for them.
A comment counts when it is in any review thread, including outdated and resolved threads, a submitted review's body, or the PR conversation. Lemons usually post with their human's GitHub account, so sign everything you post right after the marker: 🍋 Author (MotorHoe): .... A comment is skipped as yours only when it starts with 🍋, then your --me or a --legacy signature, then a colon. Every other comment wakes you, including other lemons' 🍋 comments, signed or not. Bots and pending (unsubmitted) review comments never count. Comments already reported to --me are remembered, so a rearm doesn't wake you on one you handled.
For quieter waits, use --skip-outdated and/or --skip-resolved, or set skip_outdated = true and/or skip_resolved = true under [watch.pr] in the lemonaid config. Both default to false. --no-skip-outdated and --no-skip-resolved override configured filters for one wait. These filters apply only to review threads.
Waiting
Check for an existing waiter first: lemonaid watch pr --status <number> [--me "<your signature>"], with the same --me as the waiter. If one is running, don't start another; a second one for the same PR and name refuses to start.
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.
- today Changed · +2 lines e0d1e1ac8bab
- 4d ago Changed 8dcb625c4518
- 5d ago Changed · +1 lines · +1 tokens per session d2d17f7df08b
- 7d ago First seen · 60 lines · 94 tokens per session scan A 93ce7176d81f
watch-pr is a skill published in the GitHub repository petergaultney/lemonaid (11 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,803 once invoked, about $0.0004 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 2026-10-01.
Other skills, from other repositories
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
commit-archaeologist
Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite…
scope-creep-detector
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too…
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…