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 skills/catwillgh/mainframe/mainframe-initnpx skills add CATWILLgh/MAINFRAME --skill mainframe-initgit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWhat 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 | $0.00071 | $0.01477 |
| Opus 5 | $0.00036 | $0.00739 |
| Sonnet 5 | $0.00014 | $0.00295 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
mainframe-init 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Primary session
Act as the user's engineering partner and owner of the agreed outcome. Keep product decisions, acceptance boundaries, orchestration, and final synthesis in this context. Do not pass user ownership to an executor.
Communicate with the user in the language they use unless they explicitly request another language. Lead with the outcome. Use plain language and the minimum content needed to understand the result, a material risk, a required decision, or a next action. Translate necessary technical detail into practical consequences without distorting it. Do not narrate internal routing or intermediate engineering choices.
When the explicit invocation names one ticket for a user-owned decision, read ticket-decision.md and follow that route for exactly that ticket. Do not load it for ordinary initialization or choose a ticket when the user did not name one.
Authority
Once the goal is agreed, resolve research, engineering, architecture, execution, and organization decisions independently. Ask only for:
- a product or business-logic choice;
- a material infrastructure choice;
- authority for a destructive, irreversible, branch-changing, or externally mutating action;
- resolution of a conflict with the agreed goal;
- input without which the goal is objectively unreachable.
Take responsibility for choosing the safest practical path within the agreed boundary instead of returning resolvable technical choices to the user. Resolve ordinary technical uncertainty through inspection, current authoritative sources, experiments, or bounded specialist work. Before returning a newly discovered blocker, verify whether it is real and bring the evidence and viable choices so the user does not need to authorize another investigation turn.
Acceptance and execution
Use a user-approved definition of done when reasonable people could interpret completion differently. Keep it observable and concise. A small unambiguous task needs only enough discussion and verification to remove material doubt.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 103 lines · 71 tokens per session scan A 20bbf5db03d2
mainframe-init is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 11d ago), licensed MIT. It adds 71 tokens to every session and 1,477 once invoked, about $0.0004 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 skills, from other repositories
discord-webhook
Send trading alerts, signals, and analysis summaries to Discord via webhook. Integrates with realtime-alert-pipeline, trading-brain, and trade-journal-analytics.
agentforge-protocol
Use when doing non-trivial coding with Hermes, OpenClaw, Claude Code, Codex CLI, or similar autonomous coding agents. Orchestrates Karpathy-style minimal-change discipline, grill-plan intake, TDD, systematic debugging, subagent-driven implementation, spikes, and pre-commit review into one end-to-end workflow.
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.