haiku-zap

haiku-zap is a skill for Claude Code from gigsmart/haiku-method. It costs 29 tokens per session (276 once invoked), scanned A, original, Apache-2.0.

A way to run one small software task directly through a configured execution stage. TDD means test-driven development, but this input does not say that tests are required here.

In plain words
What is it for?
Use it for bug fixes, typo corrections, configuration changes, and small refactors. It returns the selected stage, steps, agent prompts, verification procedure, and commit rules.
Why use it?
It avoids setup files and task breakdown for quick changes where you can edit and run again if needed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool.

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

Good fit Use it for bug fixes, typo corrections, configuration changes, and small refactors. It returns the selected stage, steps, agent prompts, verification procedure, and commit rules.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-zap/github.svg)](https://agentmods.dev/skills/gigsmart/haiku-method/haiku-zap)
Your own site
<a href="https://agentmods.dev/skills/gigsmart/haiku-method/haiku-zap"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-zap/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for haiku-zap

Your own site · 80×15
<a href="https://agentmods.dev/skills/gigsmart/haiku-method/haiku-zap"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-zap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 276 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 $0.00029 $0.00276
Opus 5 $0.00015 $0.00138
Sonnet 5 $0.00006 $0.00055
Haiku 4.5 $0.00003 $0.00028

Measured 9d ago against content hash c2752d4b4649, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

haiku-zap 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 9d 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-zap/SKILL.md · 15 lines

What it actually says

Zap

Run a single task directly through a stage's hat loop — no intent file, no unit decomposition, no workflow tick. Stateless: nothing is written to .haiku/. Use it for bug fixes, typos, config tweaks, and small refactors where the cost of a mistake is "edit and re-run."

Call haiku_zap { task: "<the task>", studio?, stage? }.

  • studio / stage are optional. Omit them to default to the build-class execution stage of the software studio.
  • If the tool returns zap_studio_not_found or zap_stage_not_found, surface the valid_studios / valid_stages list with AskUserQuestion, let the user pick, and call haiku_zap again with their choice.
  • Otherwise follow the returned message verbatim. It contains the resolved studio/stage, the ordered hat sequence with each hat's role, a ready-to-spawn subagent prompt per hat, and the full run/verify/commit procedure (preflight, sequential dispatch, PASS/FAIL parsing, retry cap, commit-only-on-PASS).
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. 9d ago First seen · 15 lines · 29 tokens per session scan A c2752d4b4649

Subscribe to this mod's changes

haiku-zap is a skill published in the GitHub repository gigsmart/haiku-method (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 276 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.