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/robinslange/learning-loop/quicknpx skills add robinslange/learning-loop --skill quickgit clone --depth 1 https://github.com/robinslange/learning-loopWhat 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 | $0.00063 | $0.01682 |
| Opus 5 | $0.00032 | $0.00841 |
| Sonnet 5 | $0.00013 | $0.00336 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
quick 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick: Fast Verified Answers
Overview
Answer a question quickly with web research, vault awareness, and source verification. One shot, no interactive rounds. Auto-captures noteworthy answers to the vault.
When to Use
/learning-loop:quick "how much have jaguar prices dropped recently?": direct question/learning-loop:quick: infer question from conversation context
Process
Step 1: Parse the Question
If args provided: Use as the question.
If no args: Read recent conversation. Identify the question being discussed. If no clear question, ask the user with AskUserQuestion.
Step 2: Parallel Research
Spawn both subagents in the same turn (a single message with two Agent tool calls):
Vault Scout (discovery-vault-scout):
Search the vault for what the user already knows about this topic.
Topic: <question keywords>
Vault path: {{VAULT}}/
Angle: <the specific question being asked>
Return relevant notes with content, and identify gaps.
Researcher (discovery-researcher):
Answer this specific question with web research.
Topic: <the question>
Existing knowledge: (empty: vault results not available yet)
Focus on answering the question directly, not mapping the landscape.
Source-resolve any academic claims.
Return: direct answer, supporting evidence, sources with metadata, confidence level.
Step 3: Synthesize Answer
Merge vault-scout and researcher results into a direct answer.
Structure:
- If vault has relevant notes, lead with what the user already knows and how the new info extends or updates it
- If vault contradicts web findings, flag it explicitly: "Your note X says Y, but recent evidence shows Z"
- If vault has nothing relevant, lead with the web findings
- Keep it to 3-10 sentences. Cite sources inline.
- End with confidence: high (multiple concordant sources), medium (single source or mixed), low (sparse evidence, flag uncertainty)
Tone: Conversational. Plain language. No hedging paragraphs: if uncertain, one line says so.
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.
- yesterday First seen · 151 lines · 63 tokens per session scan A b1a96f92b028
quick is a skill published in the GitHub repository robinslange/learning-loop (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,682 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.
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…