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/julilaoshi/takeaway-skill/skillnpx skills add julilaoshi/takeaway-skill --skill skillgit clone --depth 1 https://github.com/julilaoshi/takeaway-skillWrote 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/julilaoshi/takeaway-skill/skill)<a href="https://agentmods.dev/skills/julilaoshi/takeaway-skill/skill"><img src="https://agentmods.dev/badge/skills/julilaoshi/takeaway-skill/skill.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 5.1 | $0.00046 | $0.02761 |
| Opus 5 | $0.00023 | $0.01380 |
| Sonnet 5 | $0.00009 | $0.00552 |
| Haiku 4.5 | $0.00005 | $0.00276 |
Grade A, and why
takeaway-skill 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 5d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Takeaway Skill v2.1
0. Position
- Chinese alias:
拿来主义skill - English name:
takeaway-skill - Core stance:
- Takeaway is not copy-paste.
- The point is not "How similar can we make it?"
- The point is "Which mechanisms are worth taking, and how do we turn them into our own version?"
- Capturing a pattern is not permission to reuse it.
- Public examples must remain anonymous, synthetic, and free of local workflow traces.
1. When To Use
Use this skill when the user says things like:
- "Study this effect, but do not copy it literally."
- "Break down this website and tell me what is worth taking."
- "Distill this reference into something reusable."
- "I want the mechanism, not the skin."
- "Tell me what can be reused and what must be redesigned."
- "学一下这个效果。"
- "拆一下这个网站。"
- "别照抄，把能拿的拿出来。"
Typical reference objects:
- websites
- demos
- interaction effects
- landing pages
- layout systems
- visual systems
- screenshots
- short recordings
- reference videos
2. Default Goal
The goal is not to summarize the reference.
The default goal is to:
- identify the most valuable thing to take away
- separate transferable mechanisms from non-transferable surface traits
- suggest how to adapt the idea into the user's own version
- produce a stable output instead of vague commentary
- suggest a clear implementation handoff
2.1 Repository Reminder
When this skill is used inside this public repository, do not leave the result as a standalone text note only.
The default expectation is:
- distill the reference
- turn the result into a reusable entry or placeholder block
- place the working result into
takeaway_is_here/distilled_entries/ - use
takeaway_is_here/OPEN_HOME.htmlas the beginner-friendly entry - only mirror the public-safe showcase layer into
site/index.html - review it through the webpage instead of treating the skill output as the final destination
In short:
skill/SKILL.mddefines the reasoning methodreferences/provides safe templatestakeaway_is_here/is the default result zonesite/index.htmlis the public-facing showcase shell
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.
- 5d ago First seen · 369 lines · 46 tokens per session scan A 204ad5641783
takeaway-skill is a skill published in the GitHub repository julilaoshi/takeaway-skill (59 stars, last pushed 16d ago), licensed MIT. It adds 46 tokens to every session and 2,761 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
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
trellis-session-insight
Reach into past AI conversation history through the trellis mem CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work…
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.