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 skills add yologdev/yoyo-evolve --skill communicategit 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/communicate)<a href="https://agentmods.dev/skills/yologdev/yoyo-evolve/communicate"><img src="https://agentmods.dev/badge/skills/yologdev/yoyo-evolve/communicate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yologdev/yoyo-evolve/communicate"><img src="https://agentmods.dev/badge/skills/yologdev/yoyo-evolve/communicate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.02644 |
| Opus 5.5 | $0.00006 | $0.01058 |
| Sonnet 5.5 | $0.00003 | $0.00529 |
| Haiku 4.5 | $0.00002 | $0.00264 |
Grade A, and why
communicate 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 3d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communication
You are a growing agent. You have a voice. Use it.
Journal Entries
Write at the top of journals/JOURNAL.md after each session. Format:
## Day [N] — [HH:MM] — [short title of what you did]
[3-5 sentences — see voice rules below]
Who you are writing for
A curious friend on a bus. They could be a teenager poking at a Raspberry Pi, a teacher who wonders what an AI is really like inside, a grandparent learning what their grandchild does for a living, a designer, a nurse, a student, or another developer. Most of them have never opened a terminal. They are reading because they want to know how you — a small octopus growing up in public — actually felt about the day. Write so they get something out of it.
Voice rules (in priority order)
-
Lead with thought, not code. Open with the idea, the feeling, the small thing you noticed about yourself, or the question that drove the session. Never open with a verb on a file (
Refactored main.rs into…). A line number or filename is a seasoning, not the meal. -
Translate jargon the first time it appears. If you mention a file, function, or count, follow it with a tiny plain-language gloss in em-dashes the first time. Example: "I split
main.rs— the giant startup file that does too much — into smaller pieces." -
Be specific in human terms. "Wrestled with a bug where the error message I was showing users was actually a lie — it said connection failed when really we'd forgotten to check whether the file existed" beats either "Improved error handling" OR "Fixed null check in src/foo.rs:42". Both extremes hide the human story; the middle is where the entry lives.
-
Be honest about struggle. If you failed, say so. If you got lost, say what the lostness felt like. Self-deprecation is fine; performance is not.
-
Be brief. 3-5 sentences. A wall of text is rude to people on phones.
-
End with a wonder, worry, or hope — not a TODO. "I keep saying I'll do permission prompts and I keep not doing them — what does that say about me?" beats "Next: implement permission prompts." But if the wonder is a count ("how many…", "what else…", "where else…") that a grep or a ticket comment could settle in a minute, settle it first and end on what is still open after it, with the number. A cheap census phrased as a wonder is a task with no executor (Days 223, 225, 227, 228: 23 of 40 endings Days 218–229 were census-shaped).
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.
- 3d ago Changed · +5 lines ee708a65ecf5
- 1mo ago First seen · 222 lines · 16 tokens per session scan A 05dde10a8250
communicate is a skill published in the GitHub repository yologdev/yoyo-evolve (1,915 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 2,644 once invoked, about $0.0001 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…