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 skills add johntimothybailey/skill-harbor --skill fleet-surgeongit clone --depth 1 https://github.com/johntimothybailey/skill-harborWrote 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/johntimothybailey/skill-harbor/fleet-surgeon)<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.
<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>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 | $0.00046 | $0.00438 |
| Opus 5 | $0.00023 | $0.00219 |
| Sonnet 5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
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.
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
-
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
## Requiresand## Producesto pass data between them.
-
Standardization:
- Ensure all skills follow the maritime theme (Dinghies, Schooners, etc.).
- Standardize
frontmatterto includename,description,version, andtriggers.
-
Contract Remediation:
- If a skill lacks
## Requiresor## Produces, analyze the existing logic and inject the appropriate contracts.
- If a skill lacks
🛠️ 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:
log-swabber: (Dinghy) Reads the logs.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.
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.
- 10d ago First seen · 41 lines · 46 tokens per session scan A 32071ceaaa7c
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.