agentmods.dev

yolo-brief

yolo-brief is a skill for Claude Code from CoriChui/yolo. It costs 91 tokens per session (870 once invoked), scanned A, original, MIT.

A helper for recording a feature or cancelling one in a YOLO repository. It writes a brief containing the feature’s goal and checkable signs of success.

In plain words
What is it for?
Use it to create or update a feature brief, carry success criteria from a design specification, detect matching existing features, or cancel a tracked feature.
Why use it?
It gives a feature a documented purpose and clear completion checks, while avoiding duplicate briefs when the feature is already tracked. It can also use an existing approved design specification.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the yolo plugin — 5 skills shipped together

not rated 9repo 2d ago A scan 91 tokens original MIT

Good fit Use it to create or update a feature brief, carry success criteria from a design specification, detect matching existing features, or cancel a tracked feature.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/corichui/yolo/yolo-brief
View source ↗ CoriChui/yolo
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-brief
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 5 skills.

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-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/corichui/yolo/yolo-brief/github.svg)](https://agentmods.dev/skills/corichui/yolo/yolo-brief)
Your own site
<a href="https://agentmods.dev/skills/corichui/yolo/yolo-brief"><img src="https://agentmods.dev/badge/skills/corichui/yolo/yolo-brief/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.

agentmods 80×15 button for yolo-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/corichui/yolo/yolo-brief"><img src="https://agentmods.dev/badge/skills/corichui/yolo/yolo-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 870 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 $0.00091 $0.00870
Opus 5.5 $0.00036 $0.00348
Sonnet 5.5 $0.00018 $0.00174
Haiku 4.5 $0.00009 $0.00087

Measured 2d ago against content hash 3fd895bfb181, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yolo-brief 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.

.claude/skills/yolo-brief/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

yolo-brief

Record what a feature is and how you'll know it works. Designing, planning and building happen however you like; this skill only writes the brief. Rules: ../../yolo/conventions.md.

Procedure

  1. Derive the slug (conventions Naming). Before writing, check for an existing match: list workspace/features/*, compare case-insensitively, and scan existing briefs' goal for the same change (slugs drift: csv-export vs export-csv).
    • Match found → don't write a second brief. Show that feature's status (yolo-status) and update the existing brief only if the user is changing its goal or criteria.
    • Slug taken by an unrelated feature → suffix it and say so.
  2. Look for a design spec. Use one if the user points to it, if workspace/features/<slug>/spec.md exists in this checkout or on the feature branch (git show feature/<slug>:workspace/features/<slug>/spec.md), or if a spec for this feature was written and approved earlier in this conversation. Read it before writing anything.
  3. Fill the brief from ../../yolo/templates/brief.md:
    • goal: one sentence on what the user can do once it ships.
    • success_criteria: observable, checkable behaviors. With a spec, take them from its acceptance criteria, requirements or testing section, rewording any that can't be checked. Ask the user only about gaps. Without a spec, ask one short question if the user hasn't said how they'd know it works. Vague criteria make yolo-verify useless.
    • refs: repo-relative paths to the spec and plan (by convention workspace/features/<slug>/spec.md and plan.md, which may live only on the feature branch) and any ticket.
    • milestone, depends_on: only if the user mentions them.
    • created_at: the current time, ISO 8601 UTC, with real hours and minutes.
  4. Commit it alone: git add workspace/features/<slug>/brief.md && git commit -m "yolo: brief <slug>". Status is now planned.
  5. Hand over. Tell the user the next step is theirs, and print the two lines they need (if feature/<slug> already exists, e.g. the spec was written there, print git switch feature/<slug> instead of creating it):

Read the full file on GitHub · 55 lines

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. 2d ago First seen · 55 lines · 91 tokens per session scan A 3fd895bfb181

Subscribe to this mod's changes

yolo-brief is a skill published in the GitHub repository CoriChui/yolo (9 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 870 once invoked, about $0.0004 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 2026-10-26.

PlanningProject managementai-agentsanthropicclaude-code-pluginclaude-skilldeveloper-tools
Related

Other skills, from other repositories

tackle-issue

Start-of-work triage in this monorepo. Trigger on: a GitHub issue number ("tackle issue 99", "work on #42", bare #N), pasted proposal/spec text ("investigate this", "pressure-test this", "scope this"), or picker phrasing ("tackle the next issue", "what should I work on"). Read-only investigation that tries to falsify…

gtapps/claude-code-hermit · 149 tokens

hermit-scribe

File a GitHub issue or post a comment on an existing issue via a GitHub App bot identity. Use when the operator says "file as a GH issue", "open an issue for PROP-NNN", "report this to the tracker", "add a comment to issue.

gtapps/claude-code-hermit · 60 tokens

stale-proposals

Audit this repository's local proposal queue for stale entries: proposals still marked proposed, deferred, or accepted even though the work already shipped, plus old proposals whose subject has become inert. Reconcile proposals against plugin changelogs and first-parent Git history, automatically resolve only…

gtapps/claude-code-hermit · 140 tokens

atlas-present

Generate a polished HTML presentation page and Obsidian Canvas for big releases — new products, takeovers, major migrations. Non-technical audience. Use when asked to "present this", "release announcement", "show what we built", or "stakeholder update".

tonone-ai/tonone · 56 tokens

crest-narrative

Strategic narrative — write a standalone strategy memo that frames product direction, bets, and rationale for a planning horizon. Use when asked to "write a strategy doc", "product vision", "strategic narrative", "company strategy memo", "planning memo", or "explain our product direction".

tonone-ai/tonone · 64 tokens

apex-status

CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done", or at the start of a work session.

tonone-ai/tonone · 42 tokens