yolo-research

yolo-research is a skill for Claude Code from CoriChui/yolo. It costs 69 tokens per session (416 once invoked), scanned A, original, MIT.

A read-only codebase research step that gathers the files, patterns, connections, risks, and unanswered questions needed before planning a YOLO change. YOLO is a structured workflow for taking a software change from idea to verified delivery.

In plain words
What is it for?
Use it to explore how existing code works before changing it, inspect documents cited by a feature brief, and write concrete file-and-line findings for the next planning step.
Why use it?
It prevents planning from being based on guesses or a shallow view of the project. It also identifies missing background documents before they affect the plan.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the yolo plugin — 11 skills, 1 command shipped together

Good fit Use it to explore how existing code works before changing it, inspect documents cited by a feature brief, and write concrete file-and-line findings for the next planning step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/corichui/yolo/yolo-research
Install

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.

Any agent
npx skills add CoriChui/yolo --skill yolo-research
Clone the repo
git clone --depth 1 https://github.com/CoriChui/yolo

Made for: Claude Code.

Or install yolo, the plugin that ships this one along with the rest of its 11 skills, 1 command.

Wrote 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.

agentmods badge for yolo-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/corichui/yolo/yolo-research.svg)](https://agentmods.dev/skills/corichui/yolo/yolo-research)
Your own site
<a href="https://agentmods.dev/skills/corichui/yolo/yolo-research"><img src="https://agentmods.dev/badge/skills/corichui/yolo/yolo-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00416
Opus 5 $0.00034 $0.00208
Sonnet 5 $0.00014 $0.00083
Haiku 4.5 $0.00007 $0.00042

Measured 8d ago against content hash 24b52f5ec49e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

yolo-research 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 8d 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.

.claude/skills/yolo-research/SKILL.md · 27 lines

What it actually says

yolo-research

Read-only exploration. You gather the context a plan needs; you change nothing.

Inputs

  • A brief (workspace/features/<slug>/brief.md) — read goal, success_criteria, intake_refs. Or, when invoked standalone, a plain question.

Procedure

  1. Identify the relevant surface: Glob/Grep for the entities, modules, and routes named in the goal.
  2. Read the key files. Capture concrete file:line references — never vague summaries.
  3. If the brief lists intake_refs, read those files from the intake folder (intake.folder, default docs/) — search the docs engine first. Do not fetch live sources for intake; if referenced context is missing from the folder, surface the gap (a docs-engine / connector step must add it first).
  4. Note: existing patterns/conventions to follow, integration points, risks, and any open questions that would block planning.

Output

Write a concise note to workspace/features/<slug>/research.md (or return it inline when standalone) and commit it (yolo: research <slug>). Sections: Findings (with file:line), Patterns, Integration points, Risks, Open questions. Keep it tight — this feeds yolo-plan, not a human report.

Constraints

  • Read-only: never edit code, never run mutating commands.
  • No status files. You do not set or read any feature "status" — that is derived from git (.claude/yolo/conventions.md).
  • Cite file:line; do not invent APIs.
Changes

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.

  1. 8d ago First seen · 27 lines · 69 tokens per session scan A 24b52f5ec49e

Subscribe to this mod's changes

yolo-research is a skill published in the GitHub repository CoriChui/yolo (9 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 416 once invoked, about $0.0003 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.