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-decidenpx skills add CoriChui/yolo --skill yolo-decidegit 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-decide)<a href="https://agentmods.dev/skills/corichui/yolo/yolo-decide"><img src="https://agentmods.dev/badge/skills/corichui/yolo/yolo-decide.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 | $0.00055 | $0.00531 |
| Opus 5 | $0.00028 | $0.00266 |
| Sonnet 5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
yolo-decide 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 6d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yolo-decide
Reach a defensible decision via multi-perspective analysis, and record it.
Procedure
- The multi-perspective analysis runs at the billed
agents.decidetier. Confirm the decision framing before launching it — the plan-gate analogue for a decision (.claude/yolo/conventions.mdThe two gates). STOP and wait for the human here (state the framing, then pause) — do not state the framing and slide into the analysis in the same turn. Skip only if the user pre-consented. - State the decision and the options crisply.
- Argue each option from several lenses — at minimum correctness/risk, simplicity/maintainability, and pragmatism/cost. Surface the strongest case FOR and AGAINST each.
- Recommend one option, with explicit rationale, the alternatives considered, dissents (minority concerns worth recording), and revisit triggers (conditions that should reopen this).
- Write
workspace/decisions/<slug>.mdwith: decision, rationale, approach, alternatives_considered, dissents, revisit_triggers, confidence. Confirm before overwriting an existing slug. - Commit (
yolo: decision <slug>).
When to reach for bakeoff instead
yolo-decide is a single-pass, multi-lens analysis — right for most X-vs-Y calls. For a high-stakes,
hard-to-reverse decision with several defensible options (architecture, migration, tool selection), the
bakeoff skill runs a heavier judged tournament: it generates
diverse candidate solutions, auto-derives a rubric for the problem, scores each with independent judges,
and adversarially refutes the leader. If bakeoff is installed, offer it for those cases, then record its
verdict as the decision here (workspace/decisions/<slug>.md) so the trail stays in one place.
Constraints
- Read-only with respect to code; the only file you write is the decision record.
- No status field; decisions are standalone records.
- Run the multi-perspective analysis at the
agents.decidetier fromworkspace/config.yaml.
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.
- 6d ago First seen · 30 lines · 55 tokens per session scan A 8ad0ed3ab7be
yolo-decide is a skill published in the GitHub repository CoriChui/yolo (9 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 531 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
create-kr-patch
Use for Korean (Hangul) fan translations of retro console or PC games, including ROM or disc analysis, text-engine reverse engineering, Hangul fonts and custom encodings, script extraction and reinsertion, code hooks, reproducible product builds, and emulator verification. Apply it to new investigations and follow-up…
0xarchive
Query historical and real-time crypto market data from 0xArchive across two top-level venue APIs: Hyperliquid and Lighter.xyz. HIP-3 builder perps live under the Hyperliquid namespace at /v1/hyperliquid/hip3. HIP-4 outcome markets (binary prediction markets like 'Will BTC be >= X by date Y?') live at…
make-brief
Produce a local HTML page a human can actually read and decide from - a narrative decision brief, an item-by-item technical review page, or a mechanism explainer that walks through a system and its terminology. Triggers when the user says "write this up as an HTML page for me", "I don't follow, give me the full…
quiz-me
Quiz the user on root cause and intended fix BEFORE writing any non-trivial code, then verify comprehension of every change after. Use when the user asks for a bug fix, refactor, or feature and wants to stay technically sharp instead of vibe-coding. Also use when the user says "quiz me", "don't let me vibe code", or…
slopmop
Trigger when you would normally reach for pytest, gh, mypy, black, or other raw repo tooling. Redirect to sm swab, sm scour, sm buff, sm sail, sm refit, or sm doctor so remediation follows the established rails. Also trigger when asked to "install" or "set up" slop-mop in a repo, or when you find a repo with sm…
markup-mode
Add a frontend-only review/markup layer to any HTML artifact, Markdown document, or live UI so a reviewer can anchor comments to specific text or specific elements, then compile them into tagged Markdown for an agent to act on. Use when the user wants to "mark up this page", "add a review/comment layer", "annotate…