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.
npx agentmods add skills/gigsmart/haiku-method/haiku-startnpx skills add gigsmart/haiku-method --skill haiku-startgit clone --depth 1 https://github.com/gigsmart/haiku-methodWrote 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.
[](https://agentmods.dev/skills/gigsmart/haiku-method/haiku-start)<a href="https://agentmods.dev/skills/gigsmart/haiku-method/haiku-start"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-start.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00031 | $0.01766 |
| Opus 5 | $0.00015 | $0.00883 |
| Sonnet 5 | $0.00006 | $0.00353 |
| Haiku 4.5 | $0.00003 | $0.00177 |
Grade A, and why
haiku-start 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a New Intent
Process
If the user starts the intent with a referenced file — a spec, a doc, a screenshot, a path like ~/Downloads/spec.pdf, or a dragged-in attachment — read it and synthesize its relevant substance directly into the description and context you author below. NEVER store, quote, or reference the file's path in any field. An absolute path leaks the user's machine layout, and the external file won't travel with the intent — the intent must stand on its own from its own text. The path is throwaway; the synthesized content is the durable record. (Read PDFs/images natively; capture what they say, not where they live.)
-
Prelaborate — If the user's description is short (under 2 sentences) or vague, ask 2-3 targeted questions via
AskUserQuestionto understand scope, desired outcome, and constraints. Fold answers into a richer description (3-5 sentences). -
Quick context scan — Glance at the project structure (2-3 tool calls max) to understand the tech stack and project purpose. This informs studio selection later.
-
Right-size it — the escape hatch (do this BEFORE creating an intent). A full multi-stage intent is the right container for a feature. It is overkill for a bug fix, a typo, a config tweak, a copy change, or a small localized refactor — work where the whole lifecycle (design → build → review across stages) costs more than the change itself. Assess what the user actually described and pick the lightest container that fits:
- Zap-class — one localized change: a bug fix, a typo, a config/copy tweak, a small refactor; touches one or a few files; the cost of a mistake is "edit and re-run." → the right home is zap, which writes no intent and no scaffolding.
- Quick-class — a small but real task that wants one stage's hat loop (plan→do→verify) and a lightweight record, but genuinely does not span multiple stages. → the right home is quick mode (a single-stage intent).
- Feature-class — spans multiple concerns or stages, needs real decomposition / design / cross-stage review, or the user explicitly asked for the full lifecycle. → the full intent below.
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.
- 6d ago First seen · 58 lines · 31 tokens per session scan A 62c9c405e90d
haiku-start is a skill published in the GitHub repository gigsmart/haiku-method (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,766 once invoked, about $0.0002 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.
Other skills, from other repositories
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
mass-line
触发：当你需要收集多方意见、把零散反馈整合成可执行方案，或把方案带回真实使用者/执行者验证时调用；常见信号包括 stakeholder input、user feedback、意见汇总、对齐与验证。 English: Trigger when input must be gathered from many people, synthesized into a clearer plan, and returned to the affected users or executors for validation. Use this skill for a collect-synthesize-validate loop.
workflows
触发：当你面临的任务明显需要多个思想武器协作时调用；常见信号包括：从零启动新项目、攻坚复杂疑难问题、对已有方案进行迭代优化。此 skill 提供标准化的跨 skill 工作流组合，解决"应该先用哪个 skill、怎么衔接"的问题。 English: Trigger when a task clearly requires multiple skills in sequence. Use this skill to select a standard workflow that chains skills together, defines data handoff between steps, and specifies…
concentrate-forces
触发：当多个任务同时争夺时间、注意力、算力或预算，必须确定主攻方向并停止分散用力时调用；常见信号包括优先级过多、资源紧张、推进分散、需要决定先做什么。 English: Trigger when limited resources are being split across too many tasks and one main target must be chosen. Use this skill to concentrate effort, sequence work decisively, and finish a meaningful breakthrough before expanding.
protracted-strategy
触发：当目标长期、任务复杂、资源暂时处于劣势，或短期无法速胜但又不能放弃时调用；常见信号包括 long-term effort、phased plan、endurance、战略耐心、需要分阶段推进。 English: Trigger when the work is long-horizon, difficult, and unlikely to be won quickly. Use this skill to divide the effort into stages, keep strategic confidence, and accumulate small wins into overall victory.
redteam-mindset
Red-team operator discipline — the mindset corrections that separate offensive testing from defensive WAPT. Built from authorized red-team work where conservative defaults caused multiple findings to be missed and one to be incorrectly retracted. Use at the START of any red-team engagement and again whenever feeling…