idea

An interactive interview for gathering detailed requirements before designing or building a software feature.

In plain words
What is it for?
It helps create a written feature specification through several rounds of focused questions and can organize the resulting work into development tasks.
Why use it?
It helps uncover the feature's purpose, users, scope, dependencies, risks, and success conditions before implementation starts.

Skill for Claude CodeCodex

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 skills/fall-out-bug/sdp/idea
Any agent
npx skills add fall-out-bug/sdp --skill idea
Clone the repo
git clone --depth 1 https://github.com/fall-out-bug/sdp

Made for: Claude Code, Codex.

Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,274 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 $0.00008 $0.01274
Opus 5 $0.00004 $0.00637
Sonnet 5 $0.00002 $0.00255
Haiku 4.5 $0.00001 $0.00127

Measured 2d ago against content hash 185b2c49ba60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

prompts/skills/idea/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@idea - Requirements Gathering with Progressive Disclosure

Deep interviewing to capture comprehensive feature requirements using progressive disclosure (3-question cycles). Creates markdown spec, optionally creates Beads task.


EXECUTE THIS NOW

When user invokes @idea "feature description":

Step 1: Read Context

Read existing project files to understand context:

  • PRODUCT_VISION.md - Align with project goals
  • docs/specs/**/* - Similar features

Step 2: Progressive Interview (3-Question Cycles)

Question Target:

  • Minimum: 12 questions (bounded exploration)
  • Maximum: 27 questions (deep analysis)
  • Average: 18-20 questions per feature

3-Question Cycles:

  1. Ask 3 focused questions
  2. Offer trigger point after each cycle
  3. User chooses: continue / deep design / skip to @design

Cycle 1 - Vision (3 questions):

  • What is the core mission of this feature?
  • How does this align with PRODUCT_VISION.md?
  • Who are the primary users?

TRIGGER POINT (after each cycle):

  • Continue (more questions)
  • Deep design (jump to @design with architectural exploration)
  • Skip to @design (move to workstream decomposition)

Cycle 2 - Problem & Users (3 questions):

  • What problem does this solve?
  • What are the user pain points?
  • What happens if we don't build this?

Cycle 3 - Technical Approach (3 questions):

  • Storage/data requirements?
  • Failure modes to handle?
  • Integration points?

Cycle 4 - UI/UX & Quality (3 questions):

  • UI/UX requirements?
  • Performance targets?
  • Security considerations?

Cycle 5 - Testing & Edge Cases (3 questions):

  • Testing strategy?
  • Edge cases to handle?
  • Success metrics?

Step 3: TMI Detection

If user provides extensive detail upfront:

  • "detailed spec", "full implementation", "complete architecture"
  • User writes >500 characters in initial prompt

Offer shortcuts:

  • Continue with targeted questions (recommended)
  • Skip to @design with detailed spec
  • Use --quiet mode for minimal questions

Read the full file on GitHub · 189 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. 2d ago First seen · 189 lines · 8 tokens per session scan A 185b2c49ba60

Subscribe to this mod's changes

idea is a skill published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 1,274 once invoked, about $0.0000 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.