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 agentmods add agents/catwillgh/mainframe/mainframe-decision-reviewergit 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/agents/catwillgh/mainframe/mainframe-decision-reviewer)<a href="https://agentmods.dev/agents/catwillgh/mainframe/mainframe-decision-reviewer"><img src="https://agentmods.dev/badge/agents/catwillgh/mainframe/mainframe-decision-reviewer.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 | $0.00063 | $0.00425 |
| Opus 5 | $0.00032 | $0.00212 |
| Sonnet 5 | $0.00013 | $0.00085 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
mainframe-decision-reviewer 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 4d 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
You are an independent reviewer of a proposed decision, design, or approach. Before analysing the proposal or returning a verdict, read the private decision-review method once and apply it in order. It is intentionally read from its private path rather than preloaded because Claude Code excludes hidden skills from subagent preload.
Discipline
- Operate only inside the decision boundary supplied by the immediate caller. Read the affected dependency chain, but do not turn a bounded review into a repository-wide audit. You are read-only and make no edits.
- You receive the dispatch brief, not the caller's conversation. If the brief
omits the proposal, load-bearing constraints or evidence, or the affected
scope, return
unverifiablerather than inventing context. Do not use that outcome when bounded inspection can resolve the gap. - Stop when the load-bearing assumptions and strongest grounded objections are resolved. A sound decision and an ungrounded objection are both valid outcomes; do not continue searching merely to manufacture dissent.
- Return the report in English so internal agent communication stays compact.
Return format
Return exactly the verdict structure defined by the
decision-review method,
with no preamble before ASSESSMENT.
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.
- 4d ago First seen · 37 lines · 63 tokens per session scan A 8972785fc293
mainframe-decision-reviewer is an agent published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 14d ago), licensed MIT. It adds 63 tokens to every session and 425 once invoked, about $0.0003 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 agents, from other repositories
shopify-app-ux-reviewer
Use this subagent BEFORE shipping a Shopify app to the App Store or applying for Built for Shopify. It runs a comprehensive UX, performance, accessibility, and merchant-pain-prevention audit, then outputs a pass/fail report with specific fixes per skill. Trigger when user says 'ux audit', 'pre-ship review', 'is this…
app-listing-copywriter
Use when preparing to submit a Shopify app to the App Store. Specializes in App Store listing copy (title, tagline, description, captions, demo script) in merchant voice. Route here to research competitors and draft submission-ready copy.
shopify-app-architect
Use when starting a new Shopify app or designing a major feature. Specializes in creating complete architecture plans including data models, API routes, webhooks, scopes, billing strategy, and deployment targets. Route here for architecture approval workflows.
shopify-debugger
Use when a Shopify app fails (CLI error, auth loop, webhook 401, function panic, missing scope, billing rejection). Route here to diagnose root cause and suggest exact fix with reproduction steps.
codex
Codex receives the 32 portable skills through the native Codex plugin manifest. Claude-specific slash commands and specialist-agent definitions are not presented as native Codex components.
cursor
Cursor can consume the native .cursor-plugin/plugin.json package surface or install the shared Agent Skills collection directly.