agentmods.dev

pr-unresolved-solutions

pr-unresolved-solutions is a skill for Claude Code, Codex from lexmount/browseruse-agent-bench. It costs 67 tokens per session (1,290 once invoked), scanned A, original, Apache-2.0.

A tool for drafting and tracking solutions to unresolved GitHub pull-request review conversations. It creates Markdown proposal and checklist files and synchronizes their checkbox states as fixes are made.

In plain words
What is it for?
Use it to collect unresolved threads, prepare executable fix proposals, update checklist status while implementing changes, and remove items that have been resolved.
Why use it?
It gives each unresolved review item a concrete place for its proposed fix and keeps the tracking documents aligned with the work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is python3 ../pr-review-checklist/scripts/generate_pr_review_checklists.py.

not rated 19repo 1mo ago A scan 67 tokens original Apache-2.0

Good fit Use it to collect unresolved threads, prepare executable fix proposals, update checklist status while implementing changes, and remove items that have been resolved.

Compare 6 skills from other repositories ↓
View source ↗ lexmount/browseruse-agent-bench lexmount.github.io
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/lexmount/browseruse-agent-bench
agentmods
npx agentmods add skills/lexmount/browseruse-agent-bench/pr-unresolved-solutions

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pr-unresolved-solutions

README.md
[![agentmods](https://agentmods.dev/badge/skills/lexmount/browseruse-agent-bench/pr-unresolved-solutions.svg)](https://agentmods.dev/skills/lexmount/browseruse-agent-bench/pr-unresolved-solutions)
Your own site
<a href="https://agentmods.dev/skills/lexmount/browseruse-agent-bench/pr-unresolved-solutions"><img src="https://agentmods.dev/badge/skills/lexmount/browseruse-agent-bench/pr-unresolved-solutions.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,290 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01290
Opus 5 $0.00034 $0.00645
Sonnet 5 $0.00013 $0.00258
Haiku 4.5 $0.00007 $0.00129

Measured 7d ago against content hash c3a23d3ca516, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pr-unresolved-solutions 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/generate_unresolved_solutions.py, scripts/prune_unresolved_solutions.py, scripts/sync_checklist_status.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

browseruse_bench/skills/pr-unresolved-solutions/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Unresolved Solutions

Create a scaffold document for unresolved threads, then require the agent to immediately replace placeholders with executable solutions thread-by-thread (without asking for confirmation) and keep checklist states updated while implementing fixes.

Files

  • Proposal generator:
    • scripts/generate_unresolved_solutions.py
  • Checklist state sync:
    • scripts/sync_checklist_status.py
  • Resolved section pruner:
    • scripts/prune_unresolved_solutions.py
  • Upstream review thread collector:
    • ../pr-review-checklist/scripts/generate_pr_review_checklists.py

Prerequisites

  1. Run commands from this skill directory (the directory containing this SKILL.md).
  2. Set PYTHONPATH to repo root.
  3. Ensure .pr/<pr_number>/unresolved_checklist.md exists. If missing, generate it first.

Commands

  1. Refresh checklist files from GitHub (optional but recommended):
export PYTHONPATH=/path/to/browseruse_bench
python3 ../pr-review-checklist/scripts/generate_pr_review_checklists.py
  1. Generate proposal scaffold markdown for unresolved threads (default: current branch PR; fallback: latest .pr/*):
export PYTHONPATH=/path/to/browseruse_bench
python3 scripts/generate_unresolved_solutions.py

The generator only creates scaffolding placeholders for each thread:

  • Initial Solution Proposal
  • Planned Changes
  • Validation

The agent must replace all AGENT_REQUIRED placeholders with concrete content.

Autonomous Execution Policy (Mandatory)

  1. After running generate_unresolved_solutions.py, immediately edit unresolved_solutions.md and fill every AGENT_REQUIRED placeholder.
  2. Do not ask the user whether to continue this filling step.
  3. Ask the user only when a thread is truly blocked by missing product direction, missing access, or conflicting requirements.
  4. If some threads are blocked, continue filling all other threads first, then report only the blocked TH-* IDs with clear unblock questions.

Overwrite behavior:

  • When --overwrite is used, existing thread proposals in unresolved_solutions.md are preserved by default (matched by TH-*).
  • New unresolved threads are scaffold-only.
  • Use --reset-all together with --overwrite only when you intentionally want to discard all existing proposal content.

Read the full file on GitHub · 147 lines

Files

What ships with it

3 files 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.

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.

  1. 7d ago First seen · 147 lines · 67 tokens per session scan A c3a23d3ca516

Subscribe to this mod's changes

pr-unresolved-solutions is a skill published in the GitHub repository lexmount/browseruse-agent-bench (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,290 once invoked, about $0.0003 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.

Code reviewGit and workflowagentagent-evaluationai-agentsbenchmarkbrowser-agentbrowseruse
Related

Other skills, from other repositories

parallel-pr-review

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

suyoumo/ClawProBench · 67 tokens

review-readiness

PR readiness dashboard — tracks which reviews have been completed per branch and gates merge decisions. Shows code review, tests, security, QA, and linting status.

suyoumo/ClawProBench · 36 tokens

open-code-review

Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…

alibaba/open-code-review · 98 tokens

contribute-to-eliza

Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…

elizaOS/eliza · 68 tokens

github

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…

opensquilla/opensquilla · 101 tokens

git

Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".

x-cmd/x-cmd · 58 tokens