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/loopnpx skills add drn/dots --skill loopgit 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 | $0.00036 | $0.01254 |
| Opus 5 | $0.00018 | $0.00627 |
| Sonnet 5 | $0.00007 | $0.00251 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
loop 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop
Run a prompt repeatedly at a fixed interval. The main thread stays alive by sleeping between executions, spawning a background agent each cycle to do the work.
Arguments
$ARGUMENTS- interval and prompt, or a management command (list, cancel)
Syntax:
/loop <interval> <prompt or /skill>
/loop list
/loop cancel <id>
/loop cancel all
Examples:
/loop 5m check if CI is green on this PR
/loop 20m /review-pr 1234
/loop 2h check for new Sentry errors in the payments service
/loop 30s tail the deploy logs and report status
/loop list
/loop cancel 2
Context
- Current branch: !
git branch --show-current 2>/dev/null | head -1 - Git status: !
git status --short 2>/dev/null | head -10 - Working directory: !
pwd
Instructions
Step 1: Parse the Arguments
Parse $ARGUMENTS to determine the action:
Management commands:
list- Show all active loops with their ID, interval, prompt, and execution count. If no loops are active, say so.cancel <id>- Mark the specified loop as cancelled. On the next sleep cycle, the loop will detect the cancellation and stop.cancel all- Mark all loops as cancelled.
New loop:
- Extract the interval token (first argument matching the pattern below)
- Everything after the interval is the prompt to execute
Interval parsing:
NsorNsec- N seconds (minimum 30 seconds, round up if less)NmorNmin- N minutesNhorNhr- N hoursNd- N days- No interval specified - default to 10 minutes
- Convert to seconds for the sleep command
If the prompt is empty after parsing, ask the user what they want to run.
Step 2: Confirm and Initialize
Present the loop configuration:
## Loop configured
**Interval:** {human-readable interval}
**Prompt:** {the prompt to execute}
**Loop ID:** {sequential integer, starting at 1}
Starting now. First execution is immediate. Use /loop list to check status or /loop cancel {id} to stop.
Initialize tracking state:
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 · 167 lines · 36 tokens per session scan A fefc3f681439
loop is a skill published in the GitHub repository drn/dots (23 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 1,254 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…