plan-feat

A requirements-planning command for one deliverable slice, including the people involved, unusual cases, and conditions for acceptance.

In plain words
What is it for?
It creates or revises a feature `README.md`, gathers requirements through questions, links the feature to its parent idea when needed, and identifies the next planning step.
Why use it?
It turns a feature idea or roadmap item into a shared description of what should be built and how success will be judged.

Command

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/spumer/i-m-senior-developer/plan-feat
Clone the repo
git clone --depth 1 https://github.com/spumer/i-m-senior-developer
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 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 $0.00037 $0.00566
Opus 5 $0.00018 $0.00283
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00004 $0.00057

Measured 2d ago against content hash 661f02f52c24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-feat 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.

plugins/planner/commands/plan-feat.md · 29 lines

What it actually says

Активируй скилл product-discovery с видом документа feature и выполни его порядок работы от начала до конца. Для этого вида скилл загружает references/feature-mode.md.

Разбор $ARGUMENTS:

  • Свободное описание одной фичи — проработка требований новой фичи.
  • Путь к замыслу с решённым исходом feature — проработка фичи из замысла; замысел передаётся в sync флагом --parent.
  • Путь к ROADMAP.md с идентификатором элемента — фича для этого элемента порядка.
  • Путь к существующей фиче (README.md или каталогу фичи) — продолжение или пересмотр; сначала посмотри состояние через inspect.
  • Пустой аргумент — начни диалог с вопроса, что за фича.

Информационные вопросы задаются прозой порциями по два–четыре; выбор из вариантов и значимые решения — через AskUserQuestion по протоколу значимого решения скилла.

Успешный запуск всегда записывает результат в features/FEAT-NNNN-<slug>/README.md. После успешной записи в чате — только короткий итог по формату скилла: вид, путь и версия, два–четыре главных исхода, цепочка дальше. Полный документ в чат не дублируется.

Цепочка после готовой фичи (readiness: ready):

  1. /plan features/FEAT-NNNN-<slug>/README.md — архитектура по требованиям;
  2. /plan features/FEAT-NNNN-<slug>/ARCHITECTURE.md — план выполнения по архитектуре;
  3. /plan-do features/FEAT-NNNN-<slug>/ — реализация по плану.

Цепочку назови в итоге; не запускай её сам. Метод проработки и правила остановки — в скилле; не повторяй их здесь. При ошибке записи следуй разделу «Ошибка записи» скилла: подготовленное тело документа — запасной результат.

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 · 29 lines · 37 tokens per session scan A 661f02f52c24

Subscribe to this mod's changes

plan-feat is a command published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 11d ago), licensed MIT. It adds 37 tokens to every session and 566 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 2026-08-31.