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 CoriChui/yolo --skill yolo-researchgit clone --depth 1 https://github.com/CoriChui/yoloWrote 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/corichui/yolo/yolo-research)<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>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 | $0.00069 | $0.00416 |
| Opus 5 | $0.00034 | $0.00208 |
| Sonnet 5 | $0.00014 | $0.00083 |
| Haiku 4.5 | $0.00007 | $0.00042 |
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.
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) — readgoal,success_criteria,intake_refs. Or, when invoked standalone, a plain question.
Procedure
- Identify the relevant surface:
Glob/Grepfor the entities, modules, and routes named in the goal. - Read the key files. Capture concrete
file:linereferences — never vague summaries. - If the brief lists
intake_refs, read those files from the intake folder (intake.folder, defaultdocs/) — 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). - 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.
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.
- 8d ago First seen · 27 lines · 69 tokens per session scan A 24b52f5ec49e
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.
Other skills, from other repositories
multi-perspective-review
Multi-perspective collaborative review of plans or documents. Ten expert viewpoints deliberate in 3 rounds to reach consensus.
review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
plan-task
Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.
using-claude-code-kit
Session-start meta-skill. claude-code-kit-specific workflow chain, agent map, and Work system rules (generic skill-invocation discipline is shared with superpowers when present).
brainstorming
Design and spec before any planning or code. MUST USE before new features, creative work, or any implementation. Explores requirements, proposes approaches, gets design approval, then chains to plan-task.