A project-profile setup and verification tool for an agent fleet. It builds or checks a written description of a repository from files actually inspected, rather than from assumptions.

Use it after copying the fleet into a repository, when a project profile is missing or outdated, or when agents appear to be working from the wrong project structure.

It helps agents avoid reporting defects based on stale or incorrect project information. It also detects drift when a repository changes or multiple fleet copies no longer agree.

How Jm-Paunlagui/CATHERINE configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/skills/fleet-init/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINE

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jm-paunlagui/catherine/fleet-init/github.svg)](https://agentmods.dev/skills/jm-paunlagui/catherine/fleet-init)

Your own site

<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/fleet-init"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/fleet-init/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/fleet-init"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/fleet-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,697 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.

Model	Per session	Once invoked
Fable 5.1	$0.00153	$0.01697
Opus 5.5	$0.00061	$0.00679
Sonnet 5.5	$0.00031	$0.00339
Haiku 4.5	$0.00015	$0.00170

Measured 2mo ago against content hash fce6fc88cc16, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fleet-init 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 2mo 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.

.claude/skills/fleet-init/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fleet Init

Two modes. Decide which from the request, and say which you are running.

init — no usable project-profile.md for this repo, or it describes a different project. Build one from evidence.
doctor — a profile exists. Verify every claim in it against the repo, and report drift.

Both modes end with a written profile and a short report. Neither mode edits a skill file. If a project fact seems to require a skill edit, that is a finding about the skill, not a licence to edit it.

The rule this skill exists to enforce

A profile written from assumption is worse than no profile, because every agent downstream will trust it and report defects from it. Every line you write into the profile must come from a file you actually opened. Where you could not confirm something, write unverified next to it rather than a plausible guess.

Mode: init

1. Establish the surfaces

A surface is an independently buildable unit — it has its own manifest. Find them:

package.json, pyproject.toml / setup.py, go.mod, Cargo.toml, *.csproj / *.sln, pom.xml / build.gradle, Gemfile, composer.json

One manifest at the root means one surface. Several in subdirectories means a multi-surface repo — profile each separately.

2. Read the stack from the manifest, not from folder names

Take framework and major version from the dependency list, not from a README. Record what you actually found:

Signal	Tells you
`express`, `fastify`, `koa`, `@nestjs/core`	Node HTTP framework and version
`next`	App Router — check for an `app/` directory before assuming
`react` + `vite` with no `next`	Vite + React, not Next.js — this distinction routes work to a different agent
`tailwindcss` v4	Tokens live in `@theme`; there is correctly no `tailwind.config.js`
`oracledb`, `mongodb`/`mongoose`, `pg`, `mysql2`, `prisma`	Database and access layer
`vitest`, `jest`, `mocha`, `pytest`, `xunit`	Test framework — then find where tests actually live
`torch`, `tensorflow`, `scikit-learn`, `xgboost`	Which AI-group agent applies, if any
`@anthropic-ai/sdk`, `openai`, `langchain`	An LLM pipeline exists

Read the full file on GitHub · 123 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.

2mo ago First seen · 123 lines · 153 tokens per session scan A fce6fc88cc16

Subscribe to this mod's changes

fleet-init is a skill published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 153 tokens to every session and 1,697 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-05.

Project management

fleet-init next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fleet-initJm-Paunlagui/CATHERINE	Skill	2	2d ago	Apache-2.0	A	153	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

CATHERINE: Skill for Claude Code