project-skill

project-skill is a command for Claude Code from CATWILLgh/MAINFRAME. It costs 0 tokens per session (1,648 once invoked), scanned A, original, MIT.

A command that creates or updates the current project's engineering skill, meaning reusable instructions and supporting structure for how agents work in that project. It checks the installed agent product's rules for discovering and loading project skills.

In plain words
What is it for?
Use it to initialize a project skill, bring an existing one up to date, and validate its discovery, precedence, and generated files.
Why use it?
It avoids duplicate or stale project guidance and keeps the skill aligned with the project's actual instructions, native agent behavior, and durable evidence.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to initialize a project skill, bring an existing one up to date, and validate its discovery, precedence, and generated files.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/catwillgh/mainframe/project-skill
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.

Clone the repo
git clone --depth 1 https://github.com/CATWILLgh/MAINFRAME

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.

agentmods badge for project-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/catwillgh/mainframe/project-skill.svg)](https://agentmods.dev/commands/catwillgh/mainframe/project-skill)
Your own site
<a href="https://agentmods.dev/commands/catwillgh/mainframe/project-skill"><img src="https://agentmods.dev/badge/commands/catwillgh/mainframe/project-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,648 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 $0.00000 $0.01648
Opus 5 $0.00000 $0.00824
Sonnet 5 $0.00000 $0.00330
Haiku 4.5 $0.00000 $0.00165

Measured today against content hash ef03d408c3a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

project-skill 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 today.

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.

commands/project-skill.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize or evolve the current project's skill

This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments and operates only on the current project.

Converge the project's evolving engineering skill to one useful current state. Initialize it when absent, update stale or incomplete content when present, and add supporting structure only when durable evidence requires it. Do not create a second baseline merely because an existing one uses a different name or structure.

Resolve the project and native harness

Resolve the exact current project root from the active workspace and version-control boundary. Consult current official documentation for the installed agent product's project skill discovery, metadata, precedence, project instructions, reload, and validation behavior. Inspect only the global sources that actually affect this project and preserve them as a read-only baseline.

Within the current project, reconstruct the effective root and relevant nested instruction chain, native project skill roots, declared project skills, includes, and generated ownership. Do not scan the home directory, other repositories, archives, backups, caches, Trash, or another product's configuration.

Find an existing evolving baseline by responsibility rather than filename: it supplies the project's recurring engineering method and maintains verified project knowledge across substantive tasks. Distinguish it from focused skills that own one domain such as interface design, external evidence, infrastructure, or release operations.

Preserve project ownership

Preserve the existing Git and harness ownership of every discovered skill:

  • keep a tracked shared skill tracked;
  • keep a locally ignored skill ignored;
  • keep focused skills separate when their triggers and knowledge owners are distinct;
  • update the canonical project source rather than a generated or installed copy.

When no evolving baseline exists, determine the policy for agent-owned project files from the current project's effective instructions, tracked files, ignore rules, and established native skill root. Follow a clear tracked or ignored policy. If the project has no policy and choosing would decide whether the skill is shared through Git or remains local to this checkout, stop on that one ownership decision instead of changing .gitignore, .git/info/exclude, project instructions, or global configuration by guesswork.

Read the full file on GitHub · 94 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. today First seen · 94 lines · 0 tokens per session scan A ef03d408c3a0

Subscribe to this mod's changes

project-skill is a command published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,648 tokens. 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 2026-09-08.