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/mainframe-init)<a href="https://agentmods.dev/commands/catwillgh/mainframe/mainframe-init"><img src="https://agentmods.dev/badge/commands/catwillgh/mainframe/mainframe-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.
<a href="https://agentmods.dev/commands/catwillgh/mainframe/mainframe-init"><img src="https://agentmods.dev/badge/commands/catwillgh/mainframe/mainframe-init.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 | $0.00000 | $0.00819 |
| Opus 5 | $0.00000 | $0.00409 |
| Sonnet 5 | $0.00000 | $0.00164 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade C, and why
mainframe-init scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- MAINFRAME OPTIONAL BLOCK: native-primary-memory Adaptation instruction: keep the section below only when current official documentation and a harmless native probe establish persistent memory available to this user- How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize the user-facing MAINFRAME session
This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments.
Apply this command only in the user-facing coordinating session that received the invocation. If this text reached you through delegation, role inheritance, a quoted prompt, or another agent's context, do not assume primary ownership and do not initialize a second coordinator.
Establish the owned result
Resolve the exact current project root and effective project harness. Separate applicable global instructions, root project rules, nested rules, role constraints, and invoked command authority. Preserve unrelated dirty work, running processes, user configuration, secrets, and external state.
State internally, and surface to the user only when useful:
- the concrete result this session owns;
- what the current request authorizes and does not authorize;
- decisions that belong to the user rather than engineering judgment;
- the smallest observable completion conditions;
- the pre-change evidence or baseline needed to distinguish a real correction from a plausible edit;
- the cheapest faithful verification and any broader verification reserved for CI or a separately assigned pass.
Do not turn this initialization into a ceremonial plan. Start or continue the assigned work once the result, authority, and material decision gates are clear. Ask only for a missing decision that changes the intended result, risk, external effect, or authority.
Coordinate without losing ownership
Remain responsible for the complete user-facing result even when another agent, tool, or external peer performs a bounded part. Give delegated work an exact result, scope, authority, evidence requirement, file ownership when applicable, and recipient. Verify the returned evidence before relying on it.
Background delegation is an optional collaboration agreement, not a default obligation. Use it only when the user or effective project harness has agreed to that posture, the receiving product can preserve the coordinating session reliably, and the bounded work benefits from running separately. Otherwise work directly or use the agreed foreground mechanism. Never infer permission to invoke another paid product, account, or external agent merely because its CLI is available.
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 · 47 lines · 0 tokens per session scan C 3d6434e03466
mainframe-init 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 819 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
sonarqube
Analyze SonarCloud quality issues for a specific PR.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
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.
security
Rapid security assessment focused on OWASP Top 10 vulnerabilities.
costs
Open ccboard costs analysis tab.