help

A read-only project navigator that examines project state and recommends the next steps in a development workflow. It can consider paused work, plans, reviews, uncommitted changes, and other saved status information.

In plain words
What is it for?
Use it to get a ranked list of next actions and, with verbose mode, see which project sources informed those recommendations.
Why use it?
It helps you decide what to do next when a project has several possible unfinished tasks or workflow stages.

Command for Claude Code

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.

agentmods
npx agentmods add commands/ngocsangyem/meowkit/help
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 256 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00256
Opus 5 $0.00000 $0.00128
Sonnet 5 $0.00000 $0.00051
Haiku 4.5 $0.00000 $0.00026

Measured 2d ago against content hash 6ce77ef30aab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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/commands/mk/help.md · 32 lines

What it actually says

/help — Workflow Navigation (What Should I Do Next?)

Usage

/help [--verbose]

Behavior

Thin wrapper that invokes the mk:help skill — the forward-looking navigator. It scans project state (paused workflows, plans, reviews, uncommitted changes, plus checkpoint / budget / detected-model / verdict / roadmap sources) and emits a ranked top-3 of next steps mapped to the 7-phase pipeline.

Read-only: it reads state, never writes it. Backward-looking delivery status stays with /mk:status (project-manager) — this command does not duplicate it.

Execution

  1. Activate the mk:help skill.
  2. Pass --verbose through when supplied (adds full state-scan output + which additional sources were present vs skipped).

Output

A ## Status block: current phase + state, a "Recommended Next Step" (rank-1), and "Other Options" (ranks 2–3) each with a one-line rationale citing the source evidence.

See .claude/skills/help/SKILL.md for the scan sources, ranking heuristic, and the JSON-compatible next-steps shape.

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 · 32 lines · 0 tokens per session scan A 6ce77ef30aab

Subscribe to this mod's changes

help is a command published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 256 tokens. 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 2026-08-30.