sonnet-pilot

sonnet-pilot is a skill for Claude Code from zeuikli/claude-pilot-suite. It costs 143 tokens per session (4,298 once invoked), scanned A, original, MIT.

A playbook for using Sonnet, an AI model, on difficult coding and multi-step tasks through better context, delegation to sub-agents, and required self-review. It defines conditions for escalating work to Opus, another AI model.

In plain words
What is it for?
Planning complex coding work, preparing context, delegating subtasks, reviewing results, and deciding when to escalate from Sonnet to Opus.
Why use it?
It addresses missed assumptions, skipped review, and over-engineered results that can occur on complex tasks. It also provides a structured way to decide when a more capable model is warranted.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the TodoWrite tool.

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

Good fit Planning complex coding work, preparing context, delegating subtasks, reviewing results, and deciding when to escalate from Sonnet to Opus.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zeuikli/claude-pilot-suite/sonnet-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 sonnet-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 sonnet-pilot

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zeuikli/claude-pilot-suite/sonnet-pilot"><img src="https://agentmods.dev/badge/skills/zeuikli/claude-pilot-suite/sonnet-pilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,298 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 $0.00143 $0.04298
Opus 5 $0.00072 $0.02149
Sonnet 5 $0.00029 $0.00860
Haiku 4.5 $0.00014 $0.00430

Measured 10d ago against content hash 7cd8331e901e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sonnet-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 10d 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/sonnet-pilot/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sonnet Pilot — Quality-First Execution Playbook

Thesis

Deep context engineering + precise delegation = quality floor protection + predictable escalation.

Augment Code eval (2026-04): Best-quality AGENTS.md provides performance gain equivalent to one model tier (Haiku→Sonnet or Sonnet→Opus effective). Bad documentation is worse than no documentation, by ~30%. AgentOpt (arxiv 2604.06296): On HotpotQA, strongest planner alone (Opus full stack) = 31.71%; weak planner + strong solver (layered delegation) = 74.27%. Individual model capability does NOT predict ensemble performance.

What this SKILL actually does (empirically validated, A/B/C benchmark, n=5 wiki tasks, Opus 4.7 graded):

  • Sonnet + SKILL = 283/300; Sonnet Plain = 283/300; Opus = 286/300
  • SKILL net gain on routine extraction = 0: on structured wiki tasks, Sonnet already performs near-Opus without this playbook
  • SKILL value = floor protection on hard tasks: complex tasks with ambiguous requirements, multi-step agentic, cross-module design — where Sonnet without structure tends to miss assumptions, skip self-review, or produce over-engineered output

→ Think of this SKILL as insurance: no observable premium on easy days; prevents 10–30% quality loss on hard days. → If your tasks are mostly "extract facts from a structured document" → you may not see measurable gain; activate this for complex implementation and agentic tasks. → Sonnet as planner + advisor()/reviewer (Opus) on-demand > Opus full-stack for most tasks.

Cost ratio: Sonnet ($3/$15) vs Opus ($15/$75). Quality first does NOT mean always-Opus; Opus only fires when quantitative gates trigger.


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

1. Reference Pattern Technique

❌ Abstract description ✅ Point to a file
"Write a validation module" "Follow the pattern in src/auth/validator.ts"
"Add a hook similar to useUser" "Pattern: hooks/useUser.ts:42-78"
"Reference the deploy flow we used last time" "Follow <your-playbook>.md Step 3-6"

Read the full file on GitHub · 300 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. 10d ago First seen · 300 lines · 143 tokens per session scan A 7cd8331e901e

Subscribe to this mod's changes

sonnet-pilot is a skill published in the GitHub repository zeuikli/claude-pilot-suite (24 stars, last pushed 4mo ago), licensed MIT. It adds 143 tokens to every session and 4,298 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.