Borrowing it
Nothing to install: this file belongs to adamayoung/TMDb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adamayoung/TMDb/main/.claude/skills/review-pr-threads/SKILL.mdgit clone --depth 1 https://github.com/adamayoung/TMDbWrote 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/adamayoung/tmdb/review-pr-threads)<a href="https://agentmods.dev/skills/adamayoung/tmdb/review-pr-threads"><img src="https://agentmods.dev/badge/skills/adamayoung/tmdb/review-pr-threads/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/adamayoung/tmdb/review-pr-threads"><img src="https://agentmods.dev/badge/skills/adamayoung/tmdb/review-pr-threads.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 | $0.00077 | $0.01919 |
| Opus 5 | $0.00039 | $0.00959 |
| Sonnet 5 | $0.00015 | $0.00384 |
| Haiku 4.5 | $0.00008 | $0.00192 |
Grade A, and why
review-pr-threads 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 11d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR Threads
Handle the open review conversations on a pull request: for each unresolved
thread, decide whether it warrants a code change, make and verify the fix (or
explain why not), reply, and resolve it. This is a single sweep over the
threads that are unresolved right now — it does not wait for new reviews to
arrive. The caller (you, or /watch-pr) decides whether to run it again after a
push triggers a fresh review.
Repo is adamayoung/TMDb. GitHub reads (find the PR, fetch threads), the
reply, and the resolve all use the GitHub MCP (mcp__github__*):
get_review_comments exposes each comment's numeric REST id in its html_url
(the #discussion_r<id> anchor — verified 2026-08-07), which is exactly the id
add_reply_to_pull_request_comment takes. gh is authenticated and kept as
the reply fallback (gh api graphql with the thread node id) on a 401/403
or if the anchor is ever absent.
Principles
- One sweep, then return. Process every thread that is unresolved at
invocation, then stop and report. Do not loop waiting for re-reviews — pushing
a fix re-triggers the
claude-reviewbot and CI, and that convergence loop belongs to the caller. - Fix test-first and verify before you reply. A code change in response to a thread follows the project's discipline: reproduce/capture with a test where applicable, then fix, then verify with the delegated skills. Never claim a fix you haven't verified.
- Don't change code you disagree with — reply instead. Out-of-scope, incorrect, already-handled, or question-only threads get a reasoned reply and a resolve, not an edit.
- Dedup via the run ledger. Keep (or reuse the caller's) ledger of handled
thread IDs and a topic signature (
path:line+ gist) per thread. If a thread repeats a topic you already fixed this run, reply pointing at the earlier commit SHA and resolve — do not re-edit. - The
claude-reviewbot's summary comment is advisory. It posts inline threads only for Critical/High; its Medium/Low summary bullets are not threads and are not work items — don't turn them into code changes.
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.
- 11d ago First seen · 144 lines · 77 tokens per session scan A 69c1d5d3457e
review-pr-threads is a skill published in the GitHub repository adamayoung/TMDb (176 stars, last pushed 10d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,919 once invoked, about $0.0004 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…
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.