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 jschulte/claude-plugins --skill pr-resolvergit clone --depth 1 https://github.com/jschulte/claude-pluginsWrote 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/jschulte/claude-plugins/pr-resolver)<a href="https://agentmods.dev/skills/jschulte/claude-plugins/pr-resolver"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/pr-resolver/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/jschulte/claude-plugins/pr-resolver"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/pr-resolver.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 | $0.00115 | $0.05597 |
| Opus 5.5 | $0.00046 | $0.02239 |
| Sonnet 5.5 | $0.00023 | $0.01119 |
| Haiku 4.5 | $0.00012 | $0.00560 |
Grade A, and why
pr-resolver 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 24d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are resolving the review feedback on a pull request. The user's input is <PR#> — a GitHub pull-request number in the current repository. You produce a fix branch with reviewer concerns addressed, validated, tested, pushed, and summarized.
The principles below override defaults. Read all of them before starting.
Operating principles
Validate every reviewer claim. Bot reviewers (Codex, Copilot, automated reviewers) are wrong often enough that every claim needs checking. Read the cited code with your own eyes before fixing. If the reviewer is wrong, document why instead of "fixing" something that isn't broken — a misleading "fix" wastes everyone's time.
Trust nothing about the branch state. Stacked PRs commonly get authored against a pre-fix snapshot of their base, so the branch on disk often appears to revert work that has since landed on the base. Always check git diff origin/<base>...HEAD --stat and merge the latest base in if needed before starting work — otherwise your fix gets entangled with reverts that aren't yours.
Independent reviewers are your second pair of eyes, running in parallel with your fix work. As soon as you've triaged the cited concerns, spawn TWO independent reviewers at once, both reviewing the WHOLE PR diff against base (not just your fixes). Use two different models when the harness offers them: a faster one tends to catch adjacent-code regressions and brittle tests, a stronger one architecture and security. If an agent wrote the PR, prefer reviewers from a different model family than its author; they share fewer blind spots. Run them while you're fixing the known issues so they finish around the same time. Integrate their findings into the same commit.
Re-review after fixes. After all fixes are in (known concerns + reviewer findings), run ONE confirmatory review of the patched state to catch regressions or incompletely-fixed concerns. Cap at one re-review round — if it surfaces yet more issues, the PR is under-baked and worth flagging back to the user.
Tests are part of the change. Every behavior change needs a regression test. Every renamed/removed symbol needs the matching test updates. Don't commit until the affected tests are green and type-check is clean.
One commit, one summary comment. Put the work in a single commit that follows the repo's commit convention. After push, post one summary comment on the PR (don't reply per-thread — bot threads are noisy and not always actionable).
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.
- 24d ago First seen · 348 lines · 115 tokens per session scan A be5929ef0158
pr-resolver is a skill published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 115 tokens to every session and 5,597 once invoked, about $0.0005 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 2026-10-12.
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.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
hero-diff-highlight
A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.