prd-to-tasks

prd-to-tasks is a command for Claude Code from mrvladd-d/memobank. It costs 18 tokens per session (2,570 once invoked), scanned A, original, MIT.

A command that turns one or more documented features into an implementation plan and small JSON task records, grouped into work waves.

In plain words
What is it for?
Use it to plan one feature or all features after the project's requirements and design documents are ready.
Why use it?
It makes feature work easier to assign and execute by breaking broad requirements into clear, bounded tasks and checking for unresolved questions.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to plan one feature or all features after the project's requirements and design documents are ready.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mrvladd-d/memobank/prd-to-tasks
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.

Clone the repo
git clone --depth 1 https://github.com/mrvladd-d/memobank

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 prd-to-tasks

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrvladd-d/memobank/prd-to-tasks.svg)](https://agentmods.dev/commands/mrvladd-d/memobank/prd-to-tasks)
Your own site
<a href="https://agentmods.dev/commands/mrvladd-d/memobank/prd-to-tasks"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/prd-to-tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,570 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 $0.00018 $0.02570
Opus 5 $0.00009 $0.01285
Sonnet 5 $0.00004 $0.00514
Haiku 4.5 $0.00002 $0.00257

Measured 8d ago against content hash 31459a6c8bd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prd-to-tasks 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 8d 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.

skills/_shared/references/commands/prd-to-tasks.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prd-to-tasks — Feature → Implementation plan → JSON tasks

0) Вход

Ожидается $ARGUMENTS:

  • FT-<NNN> для одной фичи
  • --all для декомпозиции всех FT-* по приоритету

Если аргумент не дан:

  • interactive → попроси выбрать фичу
  • autonomous → используй --all

1) Decomposition preflight

Перед созданием или обновлением implementation plan и JSON task records проверь, что feature can be decomposed. /prd-to-tasks does not require feature clarification metadata. The normal path is /write-prd/spec-init/prd/spec-design/spec-improve FT-<NNN>/prd-to-tasks FT-<NNN>.

Для FT-<NNN>:

  1. Найди .memory-bank/features/FT-<NNN>-*.md.
  2. Прочитай frontmatter.
  3. Block only if the feature explicitly says clarification is not complete:
clarification_status: pending|blocked

Missing clarification metadata does not block decomposition. clarification_status: complete is allowed but not required.

Block if relevant unresolved markers appear in behavior / acceptance / data / contracts / security / UX / operations / verification sections:

  • NEEDS CLARIFICATION
  • TBD
  • TODO
  • ???

Do not block on those words in unrelated notes, changelog-like text, or historical context unless they affect task decomposition or verification.

If blocked:

  • interactive mode: report the feature and tell the user to run /clarify-feature FT-<NNN> or resolve the marker directly
  • autonomous mode: set terminal state HALT_CLARIFICATION_REQUIRED
  • stop immediately before decomposition
  • do not create or update implementation plans
  • do not create, update, or index task records

For --all:

  • resolve the full targeted feature set first
  • if any targeted feature is missing, has clarification_status: pending|blocked, or has blocking unresolved markers, halt before creating or updating task records for any feature
  • report all blocked feature IDs and their blockers

Read the full file on GitHub · 249 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. 8d ago First seen · 249 lines · 18 tokens per session scan A 31459a6c8bd7

Subscribe to this mod's changes

prd-to-tasks is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 2,570 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 2026-08-30.