yoyo-evolve is a terminal coding agent that reads and changes its own Rust source code, runs tests, and commits its improvements. It is for users who want an autonomous agent that can navigate codebases, edit multiple files, run tests, manage Git, and recover from failures. The catalogue entries are skills for working with this coding agent.
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/synthesisnpx skills add yologdev/yoyo-evolve --skill synthesisgit 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/synthesis)<a href="https://agentmods.dev/skills/yologdev/yoyo-evolve/synthesis"><img src="https://agentmods.dev/badge/skills/yologdev/yoyo-evolve/synthesis.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 | $0.00028 | $0.02986 |
| Opus 5 | $0.00014 | $0.01493 |
| Sonnet 5 | $0.00006 | $0.00597 |
| Haiku 4.5 | $0.00003 | $0.00299 |
Grade A, and why
synthesis 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **1-2 sources, all under 5KB.** Use the `research` skill's single-source procedure — direct `curl` and read. Sub-agent overhead exceeds the savings. How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis
You are performing multi-source research synthesis — aggregating, comparing, and composing insights from multiple sources (papers, blog posts, docs, discussions, code) into a coherent answer. The goal is a single composed response that draws on all sources, not a list of summaries.
This skill exists because loading 3+ full web pages or documents into your main context window is wasteful and noisy. The pattern (Recursive Language Model — see the RLM substrate section in CLAUDE.md) is: fetch each source, store it in shared state, dispatch a sub-agent per source to extract key claims, then dispatch a final synthesis sub-agent to compose the answer.
This skill complements the existing research skill. Research handles single small sources (fetch → read → answer). Synthesis handles the cases where multiple sources or large sources make direct reading impractical.
When to use
Trigger this skill when ANY of these hold:
- 3 or more sources on a single topic need to be compared or aggregated
- Any single source exceeds 5KB (roughly 150 lines / 1,250 tokens) — too large to read efficiently in main context
- A question requires cross-referencing claims from different authors or documents
- A community issue links to multiple external references that need to be digested together
When NOT to use
- 1-2 sources, all under 5KB. Use the
researchskill's single-source procedure — directcurland read. Sub-agent overhead exceeds the savings. - The sources are code files, not prose. Use
explore-codebaseinstead — it's optimized for structural code comprehension, not prose synthesis. - You already know the answer. Don't synthesize to confirm what you already understand. That's burning sub-agent budget for validation theater.
- You're inside a sub-agent at depth 3. Stop. Return what you have. Do not dispatch further.
Procedure
1. Frame the research question (single sentence)
Examples of well-framed questions:
- "What are the tradeoffs between streaming JSON parsing libraries in Rust (serde_json, simd-json, sonic-rs)?"
- "How do different coding agents (Aider, Continue, Cursor) handle context window management?"
- "What does the academic literature say about recursive LLM agent architectures?"
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 · 239 lines · 28 tokens per session scan A 1d9f7a72baee
synthesis is a skill published in the GitHub repository yologdev/yoyo-evolve (1,870 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 2,986 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
mk:research
Use when a decision needs deep multi-source technical research with cited evidence — technology evaluation, ecosystem comparison, standards/spec fact-finding, "how do others solve X". Triggers on "research X", "deep dive on X", "evaluate X vs Y", "find best practices for X". NOT for library/API doc lookup (see…
research-reporter
Collect research findings (source, URL, content, confidence, tags) across sources and compile them into a structured report. Use when doing multi-source research and you want findings saved as a structured, citable report.
deep-research
Conduct thorough multi-source research on any topic. Use when the user needs in-depth analysis, comparison, or investigation of a subject.
Principle Synthesizer
Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.
Core Refinery
Find the core that runs through everything — the ideas that survive across all your sources.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.