plan-idea

A command for a file-based product-discovery workflow. It turns an early idea into a written record covering the problem, evidence, important unknowns, and intended outcome.

In plain words
What is it for?
Use it to start, inspect, or revise product ideas and save the result as an IDEA document. The input can be free text or a path to an existing idea file.
Why use it?
It gives an unformed idea a consistent place and structure instead of leaving decisions scattered across a conversation. It also supports continuing or revising an existing idea document.

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-idea
Clone the repo
git clone --depth 1 https://github.com/spumer/i-m-senior-developer
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 411 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 $0.00033 $0.00411
Opus 5 $0.00016 $0.00205
Sonnet 5 $0.00007 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 2d ago against content hash c36d002b0597, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-idea 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-idea.md · 21 lines

What it actually says

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

Разбор $ARGUMENTS:

  • Свободный текст без читаемого пути — новый замысел: исходная формулировка сохраняется в документе дословно, вместе с источником.
  • Путь к существующему файлу IDEA-NNNN-<slug>.md — продолжение или пересмотр этого замысла; сначала посмотри его состояние через inspect.
  • Пустой аргумент — начни диалог с вопроса об исходной формулировке.

Значимые решения, включая решение об исходе, задавай через AskUserQuestion по протоколу скилла.

Успешный запуск всегда записывает результат в ideas/IDEA-NNNN-<slug>.md. После успешной записи в чате — только короткий итог по формату скилла: вид, путь и версия, два–четыре главных исхода, следующая команда, когда она есть. Следующую команду не выполняй сам. Полный документ в чат не дублируется.

Метод проработки живёт в скилле и его справочниках; не повторяй его 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 · 21 lines · 33 tokens per session scan A c36d002b0597

Subscribe to this mod's changes

plan-idea is a command published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 11d ago), licensed MIT. It adds 33 tokens to every session and 411 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.