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/mpaarating/ai-workflow-kit/read-laternpx skills add mpaarating/ai-workflow-kit --skill read-latergit clone --depth 1 https://github.com/mpaarating/ai-workflow-kitWhat 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 | $0.00013 | $0.00619 |
| Opus 5 | $0.00006 | $0.00309 |
| Sonnet 5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
read-later 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read Later
Save articles to your reading list with a short summary and category tag. Never lose an interesting link again.
Trigger Phrases
- "read later:"
- "save article"
- "interesting:"
- "read this:"
Workflow
Step 1: Extract URL
Parse the URL from the user's message. If no URL is provided, ask for one.
Step 2: Fetch Article
Fetch the page content and extract the article body, title, author, and publication date. Strip navigation, ads, and boilerplate.
If fetching fails (paywall, 404, timeout), save with just the URL and title from the link text. Note: "Could not fetch full content."
Step 3: Generate Summary
Write a 3-4 sentence summary of the article. Focus on:
- What the article is about (one sentence)
- The key insight or argument (one-two sentences)
- Why it matters or who it's useful for (one sentence)
Keep the summary factual. Don't editorialize.
Step 4: Categorize
Assign one category tag based on the content:
| Category | Signals |
|---|---|
| AI | Machine learning, LLMs, AI tools, agents |
| Web Dev | Frontend, backend, frameworks, APIs |
| DevOps | Infrastructure, CI/CD, deployment, monitoring |
| Career | Growth, management, interviewing, culture |
| General | Everything else |
Step 5: Save
Add to the reading list.
Using {{notes}}: Create an entry with fields: Title, URL, Summary, Category, Date Saved, Status (Unread).
Markdown fallback: Append to ~/.ai-workflow/reading-list.md:
## [Article Title](https://example.com/article)
- **Saved**: 2026-03-19
- **Category**: AI
- **Status**: Unread
Summary text here.
---
Step 6: Confirm
Respond with a brief confirmation:
Saved: "Building Agents That Actually Work" (AI)
> 3-sentence summary here.
Examples
Save from URL:
read later: https://example.com/great-article
Saved: "Great Article Title" (Web Dev)
> The article covers new patterns for server components in React 19.
> Key insight: streaming SSR reduces TTFB by 40% in benchmarks.
> Useful for frontend engineers migrating from client-side rendering.
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 · 100 lines · 13 tokens per session scan A 4be0724ea650
read-later is a skill published in the GitHub repository mpaarating/ai-workflow-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 619 once invoked, about $0.0001 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 2026-08-31.
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…