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 skills add CATWILLgh/MAINFRAME --skill mainframe-consequential-reviewgit 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/skills/catwillgh/mainframe/mainframe-consequential-review)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-consequential-review"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-consequential-review/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/skills/catwillgh/mainframe/mainframe-consequential-review"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-consequential-review.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 | $0.00038 | $0.00712 |
| Opus 5.5 | $0.00015 | $0.00285 |
| Sonnet 5.5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
mainframe-consequential-review 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review consequential decisions and results
Apply this skill before accepting a decision or completion claim when being wrong would have a material product, operational, security, financial, legal, or recovery cost. Do not wait for an explicit review request when the trigger is already evident.
Do not turn ordinary reversible work into a review ceremony. Keep the review limited to the decision or result whose acceptance matters.
Establish the acceptance claim
State neutrally what is about to be accepted, its boundary, the consequence of failure, its load-bearing assumptions, and the evidence already offered. Ignore confidence, enthusiasm, status, and claims that the answer is obvious.
Treat conversation and prior conclusions as context, not proof. Inspect the affected repository, configuration, contracts, dependency chain, or produced artifact. Verify version-sensitive external claims against current primary documentation. Use a bounded experiment when it is the cheapest faithful way to settle a material uncertainty.
Mark each material statement as observed, source-backed, inferred, or unknown. Do not upgrade an inference into evidence because it is plausible.
Try to disprove it
Identify the strongest realistic way the decision or result could fail. Work backward to concrete causes, then discard any cause already prevented by the actual system or unsupported by evidence.
Test the assumptions that must hold for acceptance. State what observation would make each assumption false and whether that observation is present, absent, or unavailable.
For a proposed decision, compare another approach only when there is a genuine decision fork. Evaluate it under the same constraints and explain where it is better or worse. Do not invent an alternative merely to appear critical.
For a completion claim, map each material acceptance condition to evidence that directly observes it. A successful build, nearby test, file presence, or structural check does not prove behavior outside what it actually measured. Evidence produced before later changes is stale for risks affected by those 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.
- 9d ago Changed · +8 tokens per session 4d965bc5c05c
- 14d ago Changed · -12 lines · -56 tokens per session bfa38113b37e
- 1mo ago First seen · 66 lines · 86 tokens per session scan A 59dc2effcc46
mainframe-consequential-review is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 712 once invoked, about $0.0002 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 2026-09-08.
Other skills, from other repositories
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode.
debug
Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
kimaki-debug
Debug and administer Kimaki itself. Use when sessions do not respond, the bot shows errors, you need the Kimaki or OpenCode service logs, want to profile the bot, restart it (only when asked), connect a model provider with kimaki login, check who may use the bot, or file a Kimaki bug report. ALWAYS load when Kimaki…
horizon-speech
Check that a microphone is usable for Horizon dictation and report which layer is at fault — no signal, bad level, or a genuine model/accent limit. Use when dictation produces wrong, unrelated, or empty text.
ast-grep
Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.