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.
git clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWrote 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/commands/catwillgh/mainframe/project-skill)<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>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 | $0.00000 | $0.01648 |
| Opus 5 | $0.00000 | $0.00824 |
| Sonnet 5 | $0.00000 | $0.00330 |
| Haiku 4.5 | $0.00000 | $0.00165 |
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.
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.
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.
- today First seen · 94 lines · 0 tokens per session scan A ef03d408c3a0
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.
Other commands, from other repositories
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
plan-ceo-review
Strategic product gate — challenge the brief, find the 10-star product hiding inside the request, before writing any code.
team
Virtual eng team orchestrator. Runs a goal end-to-end through the whole team — strategy → plan → build → QA → ship — conducted by the engineering-manager, delegating to every specialist. One entry point that connects /ceo-review, /eng-review, /qa, and /ship.
content-start
Content production session start command. Gives the daily content session a structured start, shows pending work, and sets priorities.
onboard
Project onboarding command. For adapting to a new project quickly and thoroughly.
proposal
Client proposal command. Builds a professional client proposal from project summaries. Valid for 30 days.