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 agentmods add skills/drn/dots/combine-prsnpx skills add drn/dots --skill combine-prsgit clone --depth 1 https://github.com/drn/dotsWrote 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/drn/dots/combine-prs)<a href="https://agentmods.dev/skills/drn/dots/combine-prs"><img src="https://agentmods.dev/badge/skills/drn/dots/combine-prs.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.01481 |
| Opus 5 | $0.00025 | $0.00740 |
| Sonnet 5 | $0.00010 | $0.00296 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
combine-prs 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 4d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
$ARGUMENTS- Two PR numbers or branch names to compare (e.g., "230 231" or "#230 #231")
If no arguments are provided, ask the user for two PR numbers.
Context
- Current branch: !
git branch --show-current - Git status: !
git status --short - Repo slug: !
gh repo view --json nameWithOwner --jq .nameWithOwner 2>/dev/null | head -1 - Base ref: !
git branch -r 2>/dev/null | grep -oE 'origin/(main|master)' | head -1 - Remotes: !
git remote -v 2>/dev/null | head -6
Your task
Compare two PRs that implement the same feature, analyze strengths and weaknesses, present a comparison, and on approval combine the best parts into one branch.
Step 1: Parse arguments and fetch PR metadata
Extract two PR numbers from the arguments (strip any leading "#" characters). If branch names are given instead, find their associated PRs via gh pr list.
For each PR, fetch metadata:
gh pr view <number> --json number,title,body,headRefName,baseRefName,author,state,additions,deletions,changedFiles
Verify both PRs target the same base branch and address the same feature. If they do not appear related, warn the user and ask whether to proceed.
Step 2: Fetch and analyze both diffs
For each PR, get the full diff:
gh pr diff <number>
Also read the actual changed files from each branch to understand full context (not just diff hunks). Check out each branch temporarily or use git show <branch>:<file> to read files without switching.
Analyze each PR across these dimensions:
- Files changed - which files each PR touches
- Lines added/removed - scope of changes
- Package/module placement - where new code lives, architectural fit
- Code liveness - is the code wired in and working, or dead/placeholder code
- Test coverage - what tests exist, what is covered
- Fail-fast vs graceful fallback - error handling approach
- API design - interfaces, contracts, extensibility
- Architectural implications - impact on future work, dependency direction
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.
- 4d ago First seen · 187 lines · 50 tokens per session scan A 7ed77612b8a7
combine-prs is a skill published in the GitHub repository drn/dots (23 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 1,481 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…