app-brief

app-brief is a skill for Claude Code from Cribl-Community/claude-cribl-app-plugins. It costs 24 tokens per session (2,218 once invoked), scanned A, original, Apache-2.0.

A workflow that creates or updates APP_BRIEF.md from APP_DEFINITION.md. The brief turns an app definition into detailed requirements that an implementation agent can follow.

In plain words
What is it for?
Use it in the folder containing APP_DEFINITION.md to generate or revise the brief, then review it before implementation and validation.
Why use it?
It turns a high-level app description into a clearer implementation plan and keeps that plan updated when the definition changes.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: mentions Claude Code; mentions AGENTS.md.

Part of the app-creation plugin — 4 skills shipped together

Good fit Use it in the folder containing APP_DEFINITION.md to generate or revise the brief, then review it before implementation and validation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cribl-community/claude-cribl-app-plugins/app-brief
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 Cribl-Community/claude-cribl-app-plugins --skill app-brief
Clone the repo
git clone --depth 1 https://github.com/Cribl-Community/claude-cribl-app-plugins

Made for: Claude Code.

Or install app-creation, the plugin that ships this one along with the rest of its 4 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 app-brief

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/cribl-community/claude-cribl-app-plugins/app-brief"><img src="https://agentmods.dev/badge/skills/cribl-community/claude-cribl-app-plugins/app-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,218 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 $0.00024 $0.02218
Opus 5 $0.00012 $0.01109
Sonnet 5 $0.00005 $0.00444
Haiku 4.5 $0.00002 $0.00222

Measured 11d ago against content hash da466d798868, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

app-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 11d 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.

plugins/app-creation/skills/app-brief/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-flight Check

Before proceeding, verify you are in a scaffolded Cribl app folder. If you are not, stop and tell the user: "You must run this skill from within a scaffolded Cribl app folder."

Trigger: Run this skill in the same folder where the APP_DEFINITION.md resides.

Input: Contents of APP_DEFINITION.md (and optionally existing APP_BRIEF.md if updating)

Output: A comprehensive app brief (with full editing capability) that Claude Code can use to implement the app which is stored in APP_BRIEF.md

How to Use

  1. cd into the app directory
  2. Run this skill: /app-brief
    • First run: Creates APP_BRIEF.md from the definition
    • Subsequent runs: Updates APP_BRIEF.md based on changes to APP_DEFINITION.md
  3. Review and edit the generated brief
  4. Run the /app-validate skill
  5. If validation fails, fix the brief.
  6. Pass the contents of app-brief to your agentic tool (Claude Code)

Skill Workflow

Step 1: Check for Existing Brief

  • If APP_BRIEF.md does not exist: Run the "Generate the Brief" workflow (see below)
  • If APP_BRIEF.md already exists: Run the "Update the Brief" workflow (see below)

Step 2A: Generate the Brief (First Run)

If APP_BRIEF.md does not exist, generate the implementation brief from scratch based on answers provided in APP_DEFINITION.md

# [App Name] - App Brief

## App ID
[The unique identifier for this app]

## Problem & Vision
[Summary of the problem the app solves and how users benefit]

## Target Users
[Who uses this app and what they're trying to accomplish]

## Key Workflows
### Workflow 1: [Name]
- **User sees**: [What appears on screen]
- **User does**: [What they click/configure/select]
- **Result**: [What gets created/changed/shown]
- **Permissions**: [Who can do this? Any restrictions?]

### Workflow 2: [Name]
- **User sees**: [What appears on screen]
- **User does**: [What they click/configure/select]
- **Result**: [What gets created/changed/shown]
- **Permissions**: [Who can do this? Any restrictions?]

[+ Additional workflows as needed]

## Data & Actions
**The app will fetch from Cribl:**
- [Resource type 1]: [Why? Used in which workflow?]
- [Resource type 2]: [Why? Used in which workflow?]

**The app will create/modify/delete in Cribl:**
- [Resource type 1]: [Which workflow creates/modifies/deletes this?]
- [Resource type 2]: [Which workflow creates/modifies/deletes this?]

**The app will remember (general state):**
- [State 1]: [What should be saved? When should it persist?]
- [State 2]: [What should be saved? When should it persist?]

(Or "None" if no general state)

**User-specific settings (stored per user):**
- [Setting 1]: [What is it? Which user(s) need it?]
- [Setting 2]: [What is it? Which user(s) need it?]

(Or "None" if no per-user settings)

**Secure secrets:**
- [Secret 1]: [What is it? How is it used?]
- [Secret 2]: [What is it? How is it used?]

(Or "None" if no secrets)

## UI Structure
### Overall Layout
[Recommended structure: wizard, dashboard, form, table, etc.]

### Key Screens/Pages
1. **[Screen Name]**: [What it shows, what user can interact with]
2. **[Screen Name]**: [What it shows, what user can interact with]
3. **[Screen Name]**: [What it shows, what user can interact with]

[Add more screens as needed]

## Permissions & Access
- **Who can use this app?**: [All members, or specific roles?]
- **Permission-aware behavior**: [How does the app respond if a user lacks access to an action?]

## External Integrations (if any)
- **[Service name]**: [What does the app do with it?]
- **[Service name]**: [What does the app do with it?]

(Or "None" if the app only works with Cribl)

## MVP Scope
**Must-have:**
- [Feature 1]
- [Feature 2]

**Nice-to-have (defer):**
- [Feature 1]
- [Feature 2]

**Out of scope:**
- [Feature 1]

## Edge Cases & Error Handling
- **If user lacks permission**: [What should the app show?]
- **If data is unavailable**: [What should the app show?]
- **If an action fails**: [What should the app show?]

## Implementation guidance (include this section verbatim)
- Read AGENTS.md first
- Then read openapi.json
- NEVER EVER use local storage 

---

Read the full file on GitHub · 223 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. 11d ago First seen · 223 lines · 24 tokens per session scan A da466d798868

Subscribe to this mod's changes

app-brief is a skill published in the GitHub repository Cribl-Community/claude-cribl-app-plugins (3 stars, last pushed 12d ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,218 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens