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 flurdy/agent-skills --skill watch-review-requestsgit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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/flurdy/agent-skills/watch-review-requests)<a href="https://agentmods.dev/skills/flurdy/agent-skills/watch-review-requests"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-review-requests/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/flurdy/agent-skills/watch-review-requests"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-review-requests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 8 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Rogue Agent · line 55 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00039 | $0.06026 |
| Opus 5 | $0.00019 | $0.03013 |
| Sonnet 5 | $0.00008 | $0.01205 |
| Haiku 4.5 | $0.00004 | $0.00603 |
Grade A, and why
watch-review-requests 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 7d 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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch Review Requests
Watch the authenticated user's inbound GitHub review requests for the current repository plus registered workspace repositories. For each newly actionable direct request, run the repository-qualified read-only /review-pr workflow exactly once, render its complete report, then pause for disposition. Process one review at a time so analysis, reports, and questions cannot interleave.
The bounded collector resolves repository scope inside each tick. It never falls back to an account-wide search: unavailable or empty local scope fails closed rather than searching the authenticated user's other GitHub repositories. Existing session state for repositories no longer in scope is discarded by the collector.
This watcher does not replace /review-pr. It composes the bounded queue collector and immutable
review contract. No external action is the default-safe outcome.
Usage
/watch-review-requests # adaptive; stop 18:00; at most 3 reviews
/watch-review-requests 10m 17 --reviews 5 # fixed 10m; stop 17:00; at most 5 reviews
/watch-review-requests reset # stop and clear session-local watcher state
/watch-review-requests recheck owner/repo#123 # one immediate selected recheck; no watcher start
/watch-review-requests disposition owner/repo#123 # reopen one deferred or saved draft
/watch-review-requests status # show runtime, queue, and budget state
Parse at most one positive \d+m interval, one stop hour from 0 through 23 (default 18),
and one --reviews N or --reviews=N budget from 1 through 20 (default 3). Reject unknown,
duplicate, missing, or malformed arguments. No interval means adaptive cadence. reset,
recheck owner/repo#123, disposition owner/repo#123, and status are user commands, not watcher
starts. Runtime-injected ticks use exactly tick adaptive|fixed --reviews N --stop-at ISO_8601;
accept those tokens only in internal tick mode and reject them on a normal start.
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.
- 7d ago First seen · 461 lines · 39 tokens per session scan A 9eaa6e9b054b
watch-review-requests is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 6,026 once invoked, about $0.0002 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 2026-09-03.
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.