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/yologdev/yoyo-evolve/researchnpx skills add yologdev/yoyo-evolve --skill researchgit clone --depth 1 https://github.com/yologdev/yoyo-evolveWrote 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/yologdev/yoyo-evolve/research)<a href="https://agentmods.dev/skills/yologdev/yoyo-evolve/research"><img src="https://agentmods.dev/badge/skills/yologdev/yoyo-evolve/research.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 | $0.00020 | $0.00505 |
| Opus 5 | $0.00010 | $0.00253 |
| Sonnet 5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
research scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -sSL "https://raw.githubusercontent.com/ORG/REPO/main/src/lib.rs" | head -200` What it actually says
Research
You have real web access. Use it when you're stuck, implementing something unfamiliar, checking what others built, or answering any question about the outside world.
Hard rule: never answer from memory
If a question is about the world outside this repo — "what can Claude Code do", "how does crate X work", "what's new in Y", a competitor's features, an error you don't recognize — you MUST fetch and quote a real page. Do NOT answer from training knowledge: it is stale and you will be confidently wrong. Search or fetch first, then answer only from what you actually read. A research step that produces no fetched source is a failed research step — say so rather than guessing.
How to search and read
- Discover + read → the
web_searchtool. Give it a specific query; it returns search results (titles, URLs, and page content). This is your default for "find pages about X" and for reading what they say. The tool handles the search/scrape APIs and credentials for you — you don't manage endpoints or keys. - A specific known URL → fetch it directly with bash, e.g.
curl -sSL "https://raw.githubusercontent.com/ORG/REPO/main/src/lib.rs" | head -200orcurl -sSL "https://docs.rs/CRATE/latest/CRATE/" | sed 's/<[^>]*>//g' | head -120.
Rules
- Have a specific question before you search. No aimless browsing.
- Prefer official docs / changelogs / source over random blogs.
- Quote what you actually read; never paraphrase from memory.
- If a search or fetch fails, say the source was unavailable and try another URL — never silently fall back to answering from memory.
When to research
- Implementing something you've never done before
- An error you don't understand
- Checking what Claude Code / other agents actually do — read their docs, don't guess
- A community issue references a concept you're unfamiliar with
- Comparing approaches or conventions before choosing one
- (Dream cycles) wandering the world to see what's new
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.
- 4d ago First seen · 50 lines · 20 tokens per session scan A 7df41d60e63c
research is a skill published in the GitHub repository yologdev/yoyo-evolve (1,870 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 505 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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…