haiku-ideate

haiku-ideate is a skill for Claude Code from gigsmart/haiku-method. It costs 18 tokens per session (218 once invoked), scanned A, original, Apache-2.0.

A codebase analysis workflow that looks for worthwhile improvements in performance, security, maintainability, testing, and developer experience.

In plain words
What is it for?
Use it on the whole codebase or a chosen area. It returns surviving ideas with expected impact, effort, objections, and a recommendation, plus discarded ideas and reasons.
Why use it?
It filters out ideas that are too costly, premature, risky, or complex, so you can focus on proposals that survive serious objections.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the haiku plugin — 31 skills, 2 hooks, 2 MCP servers shipped together

Good fit Use it on the whole codebase or a chosen area. It returns surviving ideas with expected impact, effort, objections, and a recommendation, plus discarded ideas and reasons.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gigsmart/haiku-method/haiku-ideate
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.

Any agent
npx skills add gigsmart/haiku-method --skill haiku-ideate
Clone the repo
git clone --depth 1 https://github.com/gigsmart/haiku-method

Made for: Claude Code.

Or install haiku, the plugin that ships this one along with the rest of its 31 skills, 2 hooks, 2 MCP servers.

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 haiku-ideate

README.md
[![agentmods](https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-ideate.svg)](https://agentmods.dev/skills/gigsmart/haiku-method/haiku-ideate)
Your own site
<a href="https://agentmods.dev/skills/gigsmart/haiku-method/haiku-ideate"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-ideate.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 218 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.00218
Opus 5 $0.00009 $0.00109
Sonnet 5 $0.00004 $0.00044
Haiku 4.5 $0.00002 $0.00022

Measured 7d ago against content hash 9a1b0c4510b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

haiku-ideate 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 7d 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.

plugin/skills/haiku-ideate/SKILL.md · 17 lines

What it actually says

Ideate

Analyze the codebase and surface high-impact improvement ideas that survive adversarial scrutiny.

  1. Scope — If a focus area is given, analyze that. Otherwise analyze the full codebase (prioritize high-churn areas).
  2. Identify opportunities: Performance, Security, Maintainability, Test Coverage, DX.
  3. Adversarial filter — Argue against each idea on cost, prematurity, complexity, alternatives, risk.
  4. Present survivors with: one-line description, impact, effort (low/med/high), strongest argument against, verdict (do it / park it). Also list discards with reasons.
  5. Next steps: Elaborate (/haiku:haiku-start), deep-dive (/haiku:haiku-ideate <sub-area>), or discard.

Be ruthless — five strong ideas beat twenty weak ones. Zero ideas is valid if nothing survives.

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. 7d ago First seen · 17 lines · 18 tokens per session scan A 9a1b0c4510b1

Subscribe to this mod's changes

haiku-ideate is a skill published in the GitHub repository gigsmart/haiku-method (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 218 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

criticism-self-criticism

A structured review method for examining completed work, criticism, and repeated mistakes. It focuses on specific evidence, causes, effects, and practical improvements.

HughYau/qiushi-skill · 197 tokens

checkup-simplify

Use this skill when the user asks for conservative cleanup of already changed source files, similar to Claude Code /simplify, but the active agent may be Cursor, Codex, Gemini, or OpenCode.

promptdriven/pdd · 0 tokens

superpowers-zh

Use when constraining AI coding with Chinese TDD methodology, systematic debugging, code review, and verification workflows. Superpowers-zh: Chinese adaptation of the Superpowers AI-assisted programming skills and methodologies.

znlgis/opengis-skills · 45 tokens

code-reviewer-chorus

Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read the integrated code, check cross-task integration / architecture / security / regression / coverage, run tests. Invoke after the last task of an idea-rooted proposal is verified; ends with a VERDICT…

Chorus-AIDLC/Chorus · 76 tokens

code-reviewer

Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read the integrated code, check cross-task integration / architecture / security / regression / coverage, run tests. Invoke after the last task of an idea-rooted proposal is verified; ends with a VERDICT…

Chorus-AIDLC/Chorus · 73 tokens

chorus-code-reviewer

Read-only Chorus code-review gateway — the final ship-time review of an Idea's aggregate code change (the whole feature across all its tasks, not one task). Fetches the Idea, its approved proposals, documents, and tasks via MCP, reviews the aggregate implementation, and posts a structured VERDICT comment on the Idea.…

Chorus-AIDLC/Chorus · 121 tokens