help

help is a skill for Claude Code from cenconq25/claude-code-app-studio. It costs 48 tokens per session (1,462 once invoked), scanned A, original, MIT.

A read-only project check that answers “what should I do next?” with one recommended skill or command based on the project’s current state.

In plain words
What is it for?
It helps choose the next step by checking session state, setup details, and the number of relevant project documents.
Why use it?
It removes the guesswork when you are stuck, returning from a break, or have just finished a task and need direction.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths.

Good fit It helps choose the next step by checking session state, setup details, and the number of relevant project documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cenconq25/claude-code-app-studio/help
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 cenconq25/claude-code-app-studio --skill help
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

Made for: Claude Code.

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 help

README.md
[![agentmods](https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/help/github.svg)](https://agentmods.dev/skills/cenconq25/claude-code-app-studio/help)
Your own site
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/help"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/help/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 help

Your own site · 80×15
<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/help"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,462 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 $0.00048 $0.01462
Opus 5 $0.00024 $0.00731
Sonnet 5 $0.00010 $0.00292
Haiku 4.5 $0.00005 $0.00146

Measured 5d ago against content hash 34d832215b56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

help 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 5d 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/help/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Help — Next Step Recommendation

Read-only. Quick, decisive. The goal is to leave the user with one specific command to run next, not a menu of options.

This skill never writes a file.


Purpose / When to Run

Run when:

  • The user types /help, "what next", "I'm stuck", "I don't know what to do"
  • The session resumed after a break and the user wants direction
  • A skill just finished and the user wants the natural next step

Distinct from /start (full guided onboarding) and /project-stage-detect (full audit). This skill is fast — under 30 seconds of work — and outputs at most a paragraph.

Inputs

  • Optional free-text question (the user's exact words)
  • The repo on disk

Outputs

  • A printed recommendation. No file writes.

Phase 1: Read the Minimum

Read only what is needed to answer:

  • production/session-state/active.md (if present) — the explicit ground truth of where the user is
  • .claude/docs/technical-preferences.md Framework field — to detect setup state
  • Glob design/concept.md, design/systems-index.md, design/prd/*.md, docs/architecture/architecture.md, production/sprints/*.md — count only, do not read content unless needed

If active.md exists and lists a clearly-defined "Next" line, that line wins over any other inference. Trust the file.


Phase 2: Match the User's Question

Categorize the user's free-text input into one of:

  1. Stuck on a specific skill — e.g., "I'm stuck on the architecture review", "design-system is asking weird questions"
  2. Lost about phase — "where am I", "what stage are we in"
  3. Specific feature question — "how do I add a screen", "where does the auth flow go"
  4. No question, just /help — generic "what next"

If the input is empty, treat as case 4.


Phase 3: Recommend

Case 1 — Stuck on a specific skill

Read whatever artifact the skill writes (e.g., for /architecture-review, read its expected output path). If the issue is missing input, point to the upstream skill that produces it. If the issue is unclear, recommend reading .claude/skills/<that-skill>/SKILL.md to understand its inputs.

Read the full file on GitHub · 154 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. 5d ago First seen · 154 lines · 48 tokens per session scan A 34d832215b56

Subscribe to this mod's changes

help is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,462 once invoked, about $0.0002 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 2026-09-03.