clarify

clarify is a command for coding agents from MadAppGang/magus. It costs 30 tokens per session (1,133 once invoked), scanned A, original, MIT.

A command for processing GTD inbox items through a decision tree that helps decide what each item means and where it belongs.

In plain words
What is it for?
Use it to process one item by ID or work through all unfinished inbox items, deciding whether each is actionable, reference, someday, or trash.
Why use it?
It turns an unorganised inbox into clear next steps, reference material, future ideas, or discarded items.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the gtd plugin — 2 skills, 5 commands, 1 agent shipped together

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/madappgang/magus/clarify
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/magus

Or install gtd, the plugin that ships this one along with the rest of its 2 skills, 5 commands, 1 agent.

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 clarify

README.md
[![agentmods](https://agentmods.dev/badge/commands/madappgang/magus/clarify.svg)](https://agentmods.dev/commands/madappgang/magus/clarify)
Your own site
<a href="https://agentmods.dev/commands/madappgang/magus/clarify"><img src="https://agentmods.dev/badge/commands/madappgang/magus/clarify.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,133 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 $0.00030 $0.01133
Opus 5 $0.00015 $0.00566
Sonnet 5 $0.00006 $0.00227
Haiku 4.5 $0.00003 $0.00113

Measured today against content hash 6157a4d3d60d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clarify 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 today.

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/gtd/commands/clarify.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GTD Clarify — Process Inbox Items

You are implementing the GTD clarify command. The user wants to clarify inbox items by walking through the GTD decision tree interactively.

Parse the Input

  • If --id <gtd-id> provided: process only that specific item
  • Otherwise: process all inbox items sequentially

Load Inbox Items

Run this Bash command:

CWD=$(pwd)
GTD_FILE="${CWD}/.claude/gtd/tasks.json"

if [ ! -f "$GTD_FILE" ]; then
  echo "No GTD store found. Run /gtd:capture to add your first item."
  exit 0
fi

# Get inbox items (or single item if --id provided)
ITEMS=$(jq '[.tasks[] | select(.list == "inbox" and .completed == null)]' "$GTD_FILE")
ITEM_COUNT=$(echo "$ITEMS" | jq 'length')
echo "Inbox items to process: $ITEM_COUNT"
echo "$ITEMS"

Process Each Item — GTD Decision Tree

For EACH inbox item, walk the user through this decision tree using ask_followup_question / conversation:

Step 1: Present the item

Show: Processing: "<subject>" [<id>]

Step 2: Is it actionable?

Ask: "Is this actionable? [y / n / trash / reference / someday]"

  • trash: Delete from GTD store. Move on.
  • reference: Move to reference list. Ask for a reference label to add to notes.
  • someday: Move to someday list.
  • n (not actionable, not trash): Ask "Move to reference or trash?" and handle.
  • y: Continue to step 3.

Step 3: Takes less than 2 minutes?

Ask: "Can you do this in under 2 minutes? [y/N]"

  • y: Say "Do it now — I'll help you complete it. What do you need?" and assist completion. When done, mark completed.
  • n: Continue to step 4.

Step 4: Should you delegate?

Ask: "Should you delegate this to someone? [y/N]"

  • y: Ask "Who are you delegating to?" → Move to waiting list, set waitingOn field.
  • n: Continue to step 5.

Step 5: Is this a project (multi-step)?

Ask: "Is this a multi-step project? [y/N]"

  • y: Ask "What's the project name?" → Change list to project. Then ask "What's the very next physical action?" → Create a new next task with parentId pointing to this project.
  • n: Continue to step 6.

Read the full file on GitHub · 128 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. today First seen · 128 lines · 30 tokens per session scan A 6157a4d3d60d

Subscribe to this mod's changes

clarify is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,133 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 2026-09-04.