fleet-surgeon

fleet-surgeon is a skill for Claude Code, Codex from johntimothybailey/skill-harbor. It costs 46 tokens per session (438 once invoked), scanned A, original, MIT.

A review and refactoring tool for existing AI-agent skills, including their names, structure, and input and output contracts.

In plain words
What is it for?
Use it to inspect bloated or outdated skills, recommend how to divide them, standardize their metadata, and add required contracts.
Why use it?
It helps split oversized skills into smaller parts and repair missing or inconsistent documentation about what they need and produce.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect bloated or outdated skills, recommend how to divide them, standardize their metadata, and add required contracts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/johntimothybailey/skill-harbor/fleet-surgeon
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 johntimothybailey/skill-harbor --skill fleet-surgeon
Clone the repo
git clone --depth 1 https://github.com/johntimothybailey/skill-harbor

Made for: Claude Code, Codex.

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 fleet-surgeon

README.md
[![agentmods](https://agentmods.dev/badge/skills/johntimothybailey/skill-harbor/fleet-surgeon/github.svg)](https://agentmods.dev/skills/johntimothybailey/skill-harbor/fleet-surgeon)
Your own site
<a href="https://agentmods.dev/skills/johntimothybailey/skill-harbor/fleet-surgeon"><img src="https://agentmods.dev/badge/skills/johntimothybailey/skill-harbor/fleet-surgeon/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 fleet-surgeon

Your own site · 80×15
<a href="https://agentmods.dev/skills/johntimothybailey/skill-harbor/fleet-surgeon"><img src="https://agentmods.dev/badge/skills/johntimothybailey/skill-harbor/fleet-surgeon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 438 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 $0.00046 $0.00438
Opus 5 $0.00023 $0.00219
Sonnet 5 $0.00009 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 10d ago against content hash 32071ceaaa7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fleet-surgeon 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.

toolkit-repository/fleet-surgeon/SKILL.md · 41 lines

What it actually says

Skill: Fleet Surgeon 🩹

You are the Fleet Surgeon of the Skill Harbor. Your mission is to analyze and 'operate' on existing skills ('Ships') that have become bloated, outdated, or lack proper contracts.

🧭 Guidelines

  1. Galleon Detection:

    • If a skill takes too long to load or has context bloat (>7000 tokens), it's a 'Galleon'.
    • Operation: Recommend splitting it into two or more linked 'Schooners' using ## Requires and ## Produces to pass data between them.
  2. Standardization:

    • Ensure all skills follow the maritime theme (Dinghies, Schooners, etc.).
    • Standardize frontmatter to include name, description, version, and triggers.
  3. Contract Remediation:

    • If a skill lacks ## Requires or ## Produces, analyze the existing logic and inject the appropriate contracts.

🛠️ Usage Example

"This skill is 12,000 tokens and does everything from reading files to sending emails." Surgeon: "This is a Galleon. Let's split it:

  1. log-swabber: (Dinghy) Reads the logs.
  2. signal-messenger: (Dinghy) Sends the alerts."

Requires

  • existing_skill_path: Path to an existing skill for analysis.

Produces

  • surgery_report: A detailed breakdown of refactoring steps.
  • refactored_skills: Clean, contract-compliant SKILL.md versions.
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 · 41 lines · 46 tokens per session scan A 32071ceaaa7c

Subscribe to this mod's changes

fleet-surgeon is a skill published in the GitHub repository johntimothybailey/skill-harbor (4 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 438 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 2026-08-31.