create-tasks-plan

create-tasks-plan is a command for Claude Code from MadaraUchiha-314/the-loop. It costs 26 tokens per session (475 once invoked), scanned A, original, MIT.

A command that turns approved requirements, design notes, and a testing plan into tasks.md, a file containing small tasks arranged by their dependencies.

In plain words
What is it for?
Use it after the requirements, design, and testing plan for a work item have been approved, to prepare an ordered work breakdown.
Why use it?
It prevents implementation tasks from drifting away from the agreed design or testing work. The dependency graph shows what must be done first and how each task will be checked.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the the-loop plugin — 2 skills, 37 commands, 2 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add MadaraUchiha-314/the-loop
Claude Code
/plugin install the-loop

Made for: Claude Code.

Or install the-loop, the plugin that ships this one along with the rest of its 2 skills, 37 commands, 2 hooks.

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 create-tasks-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/create-tasks-plan.svg)](https://agentmods.dev/commands/madarauchiha-314/the-loop/create-tasks-plan)
Your own site
<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/create-tasks-plan"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/create-tasks-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 475 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 5.1 $0.00026 $0.00475
Opus 5 $0.00013 $0.00237
Sonnet 5 $0.00005 $0.00095
Haiku 4.5 $0.00003 $0.00047

Measured 5d ago against content hash e4a9c1ac50b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-tasks-plan 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.

commands/create-tasks-plan.md · 38 lines

What it actually says

the-loop: create-tasks-plan $ARGUMENTS

Break the approved requirements + design + testing plan into a DAG of tasks — the last spec artifact. A slice of /the-loop:work-on; work-on remains the superset.

Read the the-loop skill and reference/workflow.md first. Load .the-loop/harness-config.yaml.

Steps

  1. Locate the spec. Resolve $ARGUMENTS to docs/specs/<id>/ and read requirements.md, design.md and testing-plan.md. All should be approved; if not, say so and stop.

  2. Write tasks.md from ${CLAUDE_PLUGIN_ROOT}/skills/the-loop/templates/tasks.md (${CLAUDE_PLUGIN_ROOT} = the installed plugin's root; same in Cursor): small, verifiable tasks as a DAG, each - [ ] referencing the requirement(s) it satisfies and its dependencies, plus checkpoints (tests to run). Each task's _Test:_ names a row of testing-plan.md's matrix, so the DAG and the plan cannot describe different work. Include the explicit dependency graph.

  3. Advance the phase. Set the ticket label to <phaseLabelPrefix>tasks-breakdown and mirror phase: tasks-breakdown.

  4. Reference on the ticket (link the checked-in tasks.md). tasks-breakdown has no approval gate (issue-281): the DAG is derived mechanically from the pair the human just approved at design-approval, so do not request a human review or wait for one — never set status: approved yourself; the graph advances on the artifact's shape alone.

  5. Next step: /the-loop:execute-tasks <id>.

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 · 38 lines · 26 tokens per session scan A e4a9c1ac50b2

Subscribe to this mod's changes

create-tasks-plan is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 475 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.