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/corichui/yolo/yolo-debugnpx skills add CoriChui/yolo --skill yolo-debuggit clone --depth 1 https://github.com/CoriChui/yoloWhat 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 | $0.00068 | $0.00789 |
| Opus 5 | $0.00034 | $0.00394 |
| Sonnet 5 | $0.00014 | $0.00158 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
yolo-debug 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 2d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yolo-debug
Find the true cause of a failure and fix it with evidence — not by guessing. A stateless investigation act: it produces ONE debug record plus the fix, and stores no session state.
Inputs
A bug report or failing behaviour. Derive a kebab-case slug for the record filename — there
is no brief (a debug is not a feature). Run on the current branch (see
.claude/yolo/conventions.md — a debug record never touches status derivation). If the work
turns out to add new capability rather than restore intended behaviour, hand off to
yolo-feature.
Procedure
Work the arc in order; each step's output feeds the record.
- Reproduce — get a deterministic repro (a failing test, a command, exact steps). No repro → no confirmed bug yet; say so rather than guessing.
- Hypothesize — list candidate causes; rank by likelihood and cost-to-check.
- Isolate — trace to the true cause with a concrete evidence chain (
file:line→ observed value → why it's wrong). Bisect or instrument as needed. - Fix — make the minimal change that addresses the root cause, not the symptom. Note the over-scope traps you avoided.
- Verify — the failing reproducer now passes, the symptom is gone, and the wider suite stays green.
The Iron Law: no root-cause claim without a file:line evidence chain; no fix without a
failing reproducer that the fix flips to green; never patch the symptom while the cause stands.
Failing-test-first is the default — if a bug is genuinely not unit-testable (config, perf,
flake, environment), record why in the artifact and substitute the strongest available
evidence (a before/after command, a metric, a log excerpt).
Discipline (the traps that end investigations early)
- "It's probably X" without checking is a guess, not a cause — confirm before you fix.
- The first plausible cause is not always the cause — confirm it explains the symptom fully.
- A green fix with no reproducer proves nothing — you may have moved the bug, not killed it.
- Red flags to stop and re-examine: the fix touches unrelated files; the bug "can't be reproduced but is fixed"; the explanation needs a "this should never happen".
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.
- 2d ago First seen · 51 lines · 68 tokens per session scan A 49ec6f8a1c98
yolo-debug is a skill published in the GitHub repository CoriChui/yolo (9 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 789 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
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
social-post
學習使用者的 Facebook／Instagram／YouTube／Threads／X 語氣與受眾，規劃、撰寫、確認後發佈內容；以已登入 Chrome 受控掃描、草擬及回覆 FB／IG／Threads 留言；並作為流量、留存與轉化的結構化帳本。使用者說「發文」「用我的口氣」「回覆留言」「自動回留言」「掃留言」「查流量」「演算法」「把數據訓練進去」「比較貼文」「優化 pattern」時使用。.
privacy-jp
日本サービス向け（일본 서비스용） プライバシーポリシー・利用規約・同意モーダル・Cookieバナー 자동 생성. 個人情報保護法(APPI)·消費者契約法·特定商取引法 반영. Next.js 1316 프로젝트 대상.
higgsfield
Use this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Sora 2, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema…
higgsfield-camera
Use when the user asks about camera movements, shot types, or how to describe camera behavior in a Higgsfield prompt. Contains all named camera controls with descriptions, best use cases, and example prompt phrases.