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-pr-feedbackgit 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-pr-feedback)<a href="https://agentmods.dev/skills/flurdy/agent-skills/watch-pr-feedback"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-pr-feedback/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-pr-feedback"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-pr-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 9 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.
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 | $0.00047 | $0.04928 |
| Opus 5 | $0.00023 | $0.02464 |
| Sonnet 5 | $0.00009 | $0.00986 |
| Haiku 4.5 | $0.00005 | $0.00493 |
Grade A, and why
watch-pr-feedback scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
feedback inventory: never invoke `gh api` directly, use `curl`, or call a bulk compatibility How it starts
The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch PR Feedback
Watch open PRs for normalized feedback events, independently validate new actionable claims, and
render a concise queue. This skill composes /pr-status discovery and inventory behavior with the
read-only validation boundary from /review-comments; it does not replace either skill and does
not create another scheduler.
Usage
/watch-pr-feedback # adaptive, read-only, stop at 18:00
/watch-pr-feedback attended # adaptive, attended, stop at 18:00
/watch-pr-feedback 10m 17 # fixed 10m, read-only, stop at 17:00
/watch-pr-feedback attended 5m 17 # fixed 5m, attended, stop at 17:00
/watch-pr-feedback reset # clear this session's seen/retry state
/watch-pr-feedback recheck # one read-only validation pass, ignoring seen state
/watch-pr-feedback status # show runtime and bounded state summary
Parse at most one mode (attended; absent means read-only), one positive \d+m fixed interval,
and one stop hour from 0 through 23 (default 18). No interval means adaptive mode. Reject
unknown or duplicate arguments. Resolve today's stop hour in local time and do not start at or past
it.
Safety boundary
Default read-only mode never prompts and never edits code, changes the working tree, runs commands that may create build artifacts, publishes GitHub content, changes thread state, or changes Git history. It may read local files and metadata, inspect a PR diff, existing tests, and CI. Attended mode has the same mutation boundary; its question only controls acknowledgment and watcher state. A semantic classification, validation outcome, or answer is never permission to mutate code or GitHub. Stop the watcher and invoke the appropriate attended workflow separately for any action.
Do not switch branches, fetch remotes, or create a checkout. Never assume the current directory is the checkout for a PR merely because repository names look related. Do not run shell, Git, filesystem, workspace, or authentication preflight probes when starting the watcher. In ticks, never improvise a shell loop or workspace scan; use only the allowlisted checkout helper below.
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 · 386 lines · 47 tokens per session scan A 25d678461a34
watch-pr-feedback is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 4,928 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.