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/prnpx skills add drn/dots --skill prgit clone --depth 1 https://github.com/drn/dotsWhat 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 | $0.00039 | $0.04055 |
| Opus 5 | $0.00019 | $0.02027 |
| Sonnet 5 | $0.00008 | $0.00811 |
| Haiku 4.5 | $0.00004 | $0.00405 |
Grade A, and why
pr 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 2d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Current branch: !
git branch --show-current - Git status: !
git status --short
Phase Protocol
This skill participates in a phase chain. Read ~/.claude/skills/_shared/resources/phase-protocol.md for the full protocol.
Before creating the PR: Check .context/phases/ for prior artifacts. If any exist, use them to enrich the PR description:
plan-*.mdorthink-*.md→ use the goal/summary for PR contextbuild-*.md→ use the changes summary and deviationsreview-*.md→ reference review findings and their resolutiontest-*.md→ include test results and coverage metrics
After the PR is created and green: Write a ship-{ts}.md artifact to .context/phases/ (create with mkdir -p .context/phases). The Detail section should include the PR URL, CI status, and any fixes applied. The Handoff section should note the PR number for /merge.
Do NOT git add or commit the ship-{ts}.md artifact (or any .context/ file) into the PR. It is agent-local scratch for cross-phase handoff, not reviewable content — a ship-*.md in the PR diff is a defect reviewers will flag. In every commit step below (Step 1 and Step 4b), stage only the real change; never use git add -A or git add . (they sweep in .context/). As a belt-and-suspenders safeguard, add .context/ to the repo's .gitignore so the artifact can never be swept in.
Your task
Open a PR for the current branch, then loop until CI is fully green and all review comments are addressed. Do not return until the PR is in a mergeable, green state.
If a PR already exists for this branch, skip straight to Step 3 — even if there are no local changes or commits. Your job is to get the PR to a green, mergeable state, not just to open it. Never abort when a PR exists.
Step 0: Check for existing PR
Determine the upstream repo slug (owner/name) — use upstream remote if it exists, otherwise origin. Use gh pr list --repo <owner/repo> --head '<fork-owner>:<branch>' --state open --json number,url to check if a PR already exists. If one exists, note the PR number and skip to Step 3.
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.
- 2d ago First seen · 281 lines · 39 tokens per session scan A 81af6a789e76
pr is a skill published in the GitHub repository drn/dots (23 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 4,055 once invoked, about $0.0002 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…