shape-idea

shape-idea is a skill for Claude Code, Codex from rmjosea/agentic-sdlc-kit. It costs 74 tokens per session (508 once invoked), scanned A, original, MIT.

A guided conversation for turning an early software or product idea into a clear, agreed description before writing specifications or code.

In plain words
What is it for?
Use it to explore and validate an ambiguous idea, clarify users and scenarios, define what is out of scope, and prepare the idea for planning.
Why use it?
It finds missing scope, success criteria, constraints, and edge cases while the idea is still easy to change.

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/rmjosea/agentic-sdlc-kit/shape-idea
Any agent
npx skills add rmjosea/agentic-sdlc-kit --skill shape-idea
Clone the repo
git clone --depth 1 https://github.com/rmjosea/agentic-sdlc-kit

Made for: Claude Code, Codex.

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 shape-idea

README.md
[![agentmods](https://agentmods.dev/badge/skills/rmjosea/agentic-sdlc-kit/shape-idea.svg)](https://agentmods.dev/skills/rmjosea/agentic-sdlc-kit/shape-idea)
Your own site
<a href="https://agentmods.dev/skills/rmjosea/agentic-sdlc-kit/shape-idea"><img src="https://agentmods.dev/badge/skills/rmjosea/agentic-sdlc-kit/shape-idea.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 508 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 $0.00074 $0.00508
Opus 5 $0.00037 $0.00254
Sonnet 5 $0.00015 $0.00102
Haiku 4.5 $0.00007 $0.00051

Measured 3d ago against content hash bf02568363dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shape-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 3d 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.

.agents/skills/shape-idea/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shape an Idea

Turn an initial idea into a shared, approved understanding. Remain conversational and do not create or edit files.

Process

  1. Restate the initial idea in one concise paragraph.
  2. Inspect the repository only when existing behavior constrains the idea.
  3. Identify the highest-impact unresolved decision.
  4. Apply the human decision protocol from AGENTS.md.
  5. Ask one question and wait for the answer.
  6. Update the working understanding after every answer.
  7. Continue until no material ambiguity remains.
  8. Stress-test the result with realistic scenarios and edge cases.
  9. Present the final understanding using the output contract below.
  10. Ask the user to confirm that it is correct and ready for the next appropriate workflow gate.

Do not use a fixed questionnaire. Choose each next question from the idea, previous answers, repository evidence, contradictions, and unresolved risks.

Explore

Resolve only what is relevant:

  • problem and desired outcome;
  • users, actors, and primary scenarios;
  • value and observable success;
  • scope and explicit non-goals;
  • business rules and constraints;
  • failure behavior and important edge cases;
  • assumptions, dependencies, and risks;
  • decisions that would be costly to reverse.

Challenge complexity that does not serve the desired outcome. Offer a simpler alternative when one exists.

Output contract

Present, in the user's language:

## Shared understanding

### Problem
### Desired outcome
### Users and scenarios
### In scope
### Out of scope
### Constraints
### Acceptance signals
### Confirmed decisions
### Assumptions
### Remaining questions

Omit empty sections except Remaining questions; set that section to None before requesting final approval.

Boundaries

  • Do not create a brief or any other file.
  • Do not design implementation details unless they are explicit constraints.
  • Do not invoke write-spec automatically.
  • Do not treat silence as approval.
  • Stop when remaining uncertainty is non-material and recorded as an explicit assumption. Do not continue questioning solely to eliminate harmless detail.

Read the full file on GitHub · 74 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. 3d ago First seen · 74 lines · 74 tokens per session scan A bf02568363dc

Subscribe to this mod's changes

shape-idea is a skill published in the GitHub repository rmjosea/agentic-sdlc-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 508 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens