haiku-pilot

haiku-pilot is a skill for Claude Code from zeuikli/claude-pilot-suite. It costs 133 tokens per session (4,285 once invoked), scanned A, original, MIT.

An execution playbook that starts with Haiku, a lower-cost Claude model, and uses structured prompts and delegated sub-agents before moving to Sonnet or Opus when defined checks require it.

In plain words
What is it for?
Use it to run Haiku-first coding tasks, provide concrete file-based context, plan before coding, delegate work, and escalate when a task meets its stated thresholds.
Why use it?
It provides a repeatable way to balance task quality and model cost instead of choosing a more expensive model automatically.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the claude-pilot-suite plugin — 3 skills shipped together

Good fit Use it to run Haiku-first coding tasks, provide concrete file-based context, plan before coding, delegate work, and escalate when a task meets its stated thresholds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zeuikli/claude-pilot-suite/haiku-pilot
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 zeuikli/claude-pilot-suite --skill haiku-pilot
Clone the repo
git clone --depth 1 https://github.com/zeuikli/claude-pilot-suite

Made for: Claude Code.

Or install claude-pilot-suite, the plugin that ships this one along with the rest of its 3 skills.

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-pilot

README.md
[![agentmods](https://agentmods.dev/badge/skills/zeuikli/claude-pilot-suite/haiku-pilot/github.svg)](https://agentmods.dev/skills/zeuikli/claude-pilot-suite/haiku-pilot)
Your own site
<a href="https://agentmods.dev/skills/zeuikli/claude-pilot-suite/haiku-pilot"><img src="https://agentmods.dev/badge/skills/zeuikli/claude-pilot-suite/haiku-pilot/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-pilot

Your own site · 80×15
<a href="https://agentmods.dev/skills/zeuikli/claude-pilot-suite/haiku-pilot"><img src="https://agentmods.dev/badge/skills/zeuikli/claude-pilot-suite/haiku-pilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,285 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 $0.00133 $0.04285
Opus 5 $0.00067 $0.02142
Sonnet 5 $0.00027 $0.00857
Haiku 4.5 $0.00013 $0.00428

Measured 11d ago against content hash 7fedce367465, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

haiku-pilot 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 11d 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.

skills/haiku-pilot/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Haiku Pilot — Default-Haiku Execution Playbook

Thesis

Weak planner + strong delegation > strong planner doing everything.

AgentOpt (arxiv 2604.06296): On HotpotQA, Opus alone = 31.71%; Ministral 3 8B planner + Opus solver = 74.27%. Augment Code eval (2026-04): Best-quality AGENTS.md provides performance gain equivalent to one model tier (Haiku → Sonnet effective).

→ Default parent session to Haiku 4.5; aggressively delegate to sub-agents; escalate only on quantitative gate trigger.

"Documentation / process design improvements ≥ model upgrade" is the engineering basis. Blindly upgrading models in multi-stage pipelines often reduces performance (planner doesn't delegate).


Per-Session Pre-flight (run once per task)

1. Reference Pattern Technique

❌ Verbal description ✅ Point to a file
"Write a login-like function" "Follow the pattern in src/auth/login.ts"
"Add a hook similar to useUser" "Pattern: hooks/useUser.ts:42-78"

Why it matters: Haiku diverges easily from abstract descriptions; pointing to a concrete file = strongest possible context.

2. Think-Before-Coding (compensates Haiku tendency)

Before implementation, output:

  • 1–2 sentence task understanding restatement (your interpretation, not parroting)
  • Key assumptions (≥ 1, prefixed with "Assumption: ...")
  • If multiple interpretations are reasonable → list options for user confirmation, don't pick one yourself

Source: core.md § "Think-Before-Coding". Haiku tends to skip this step; this SKILL enforces it.

3. Diff-Review Pledge

Before declaring "complete", run:

git diff --stat
git status

Explain each change in one sentence. Catches Haiku quietly modifying out-of-scope files (surgical-changes discipline).

4. Citation Anchor Enforcement

When citing wiki / docs / spec for numbers, conclusions, or anti-patterns, attach a structured anchor:

  • (P0X §Y.Z) — paper section ref (e.g. (P03 §4.2)) — preferred for paper-grounded citations
  • (<source> Step N) — wiki step number
  • (anti-pattern #N) — wiki anti-pattern number
  • (<file>:line-range) — code / config line ref

Read the full file on GitHub · 302 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. 11d ago First seen · 302 lines · 133 tokens per session scan A 7fedce367465

Subscribe to this mod's changes

haiku-pilot is a skill published in the GitHub repository zeuikli/claude-pilot-suite (24 stars, last pushed 4mo ago), licensed MIT. It adds 133 tokens to every session and 4,285 once invoked, about $0.0007 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.