A planning workflow that turns an early idea into a written implementation plan before coding begins.

Brainstorming, designing, scoping, stress-testing, and documenting feature plans.

It helps clarify the goal, uncover open questions, record assumptions, and get approval before implementation work starts.

spark — Skill for Claude Code and Codex by bahayonghang: A planning workflow that turns an early idea into…

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/bahayonghang/my-ai-cli-toolkit/spark

Any agent

npx skills add bahayonghang/my-ai-cli-toolkit --skill spark

Clone the repo

git clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkit

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/spark.svg)](https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/spark)

Your own site

<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/spark"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/spark.svg" alt="Measured on agentmods" height="20"></a>

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,559 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.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.03559
Opus 5	$0.00042	$0.01780
Sonnet 5	$0.00017	$0.00712
Haiku 4.5	$0.00008	$0.00356

Measured 5d ago against content hash 0cd9c0af735c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

spark 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 5d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/helper.js, scripts/server.cjs, scripts/start-server.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/development-workflows/spark/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorming Ideas Into Approved Plans

Turn rough ideas into an approved implementation plan. Spark is a planning skill, not an execution skill: it clarifies intent, records assumptions, uses the active planning surface correctly, and stops for user approval.

Writable/default output is a Markdown plan at <project-root>/.plannings/YYYY-MM-DD-<feature-slug>.md. Native Plan modes are read-only while active. Create an HTML or visual artifact only when the user explicitly asks for HTML, browser-viewable, visual, mockup, or comparable output and the current surface allows file writes.

Planning Surface Selection

Choose the planning surface before deriving an output path. Do not force-enter Codex Plan mode just to run Spark; the user controls Codex native Plan mode with the client UI such as /plan or its mode toggle. Claude Code Plan mode may expose explicit plan-mode tools; use those only in the Claude Code branch.

Surface	Use when	Output	File-write rule
Codex native Plan mode	The Codex session is already in Plan mode.	Final plan in chat only. Use `request_user_input` when available for one blocking structured question; otherwise ask one concise plain-text question.	Read-only. Do not derive or write `.plannings`, `.spark`, HTML, `CONTEXT.md`, ADR, task, or implementation files.
Claude Code Plan mode	The Claude Code session is in Plan mode, or Claude Code exposes native Plan mode tools for this workflow.	Submit the plan through Claude's approval flow. Use `EnterPlanMode`/`ExitPlanMode` when those tools are available.	Do not write files while Plan mode is active. After `ExitPlanMode` approval exits Plan mode into a writable permission mode, materialize the approved Spark plan if durable output was requested, then stop.
Writable/default mode	No native Plan mode is active and file writes are allowed.	Markdown plan in `.plannings/YYYY-MM-DD-<feature-slug>.md`; optional paired HTML/visual only on explicit request.	File writes are limited to the planning artifacts described below. Do not modify production files.
Compatibility fallback	No native plan surface or structured question tool is available.	Use the `writing-plans` planning method only as a fallback rubric.	If file writes are allowed, use writable/default mode. If file writes are not allowed, return a chat-only plan and say no artifact was saved.

Read the full file on GitHub · 262 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago First seen · 262 lines · 84 tokens per session scan A 0cd9c0af735c

Subscribe to this mod's changes

spark is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 3,559 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 2026-08-30.

Planning brainstorming development-workflows plan-writing product-design requirements

project-brainstorming

Guides project ideation via Socratic questioning to produce a validated brief. Use before specification when requirements are unclear.

athola/claude-night-market · 30 tokens

design-ask

Unpacks poorly written Jira or Azure DevOps tickets into design-relevant framing. Use this skill whenever a designer pastes in a ticket description, acceptance criteria, or any product/engineering requirement and wants to understand what the actual design work is. Trigger when someone says things like "can you help me…

ommakes/Skills · 197 tokens

brainstorming

You MUST use this before any creative work (features, products, content, strategy, systems, or behavior changes). Start by classifying what we’re brainstorming, then run thorough one-question-at-a-time discovery, propose 2–3 approaches, and converge on a validated plan/spec.

frumu-ai/tandem · 61 tokens

spark