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-researchgit 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-research)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-research"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-research/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-research"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-research.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 | $0.00033 | $0.00806 |
| Opus 5.5 | $0.00013 | $0.00322 |
| Sonnet 5.5 | $0.00007 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
mainframe-research 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External research
Apply this method when the active work matches the description, whether you are the primary researcher, a delegated specialist, or a reviewer. Follow the scope and authority supplied through the current execution path; this skill does not expand either.
Treat certainty as claim-specific. Keep facts supplied by the current recipient, local observations, externally verified facts, attributed statements, calculations, inferences, and unknowns visibly distinct. External sources do not prove the state of a local project or environment.
Establish the research boundary
State the bounded question and the date on which the answer must be current. Resolve the exact entities, jurisdiction, product or dataset version, surface, reference period, comparison baseline, units, and definitions that could change the answer. Return a missing load-bearing input to the current recipient when it cannot be recovered without guessing.
Separate claims that need different evidence. Read a reference when its domain-specific method is needed, reusing material already loaded:
- Software documentation for products, APIs, libraries, tools, protocols, releases, compatibility, incidents, and security notices.
- News and current events for events, announcements, disputes, allegations, investigations, and developing public claims.
- Quantitative data for statistics, prices, rates, currencies, surveys, forecasts, ratios, benchmarks, and calculated comparisons.
A claim may require more than one reference. Do not force the whole question into a single domain.
Build the evidence chain
Prefer the closest controlling primary source for each claim. Add a genuinely independent source when the claim is disputable, interpretive, fast-changing, supplied by an interested party, or consequential enough that one evidence chain is fragile. One authoritative controlling record may be sufficient for a canonical fact.
What ships with it
3 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.
- 9d ago Changed · +6 tokens per session 80354b363677
- 14d ago Changed · +4 lines · -42 tokens per session e77761134e59
- 1mo ago First seen · 47 lines · 69 tokens per session scan A 5eb8e2d6b83f
mainframe-research is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 806 once invoked, about $0.0001 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
minions
PM Ops — orchestrator of the minions AI subagent team. Single entry point: decomposes requests, delegates to minions- subagents in parallel or sequence, aggregates output.
optimize-goal
Use when the user wants to review, critique, tighten, or enhance an existing goal.md file (a written spec/prompt authored for a /goal command instead of typed into chat) before it gets executed — including requests like "review this goal.md", "enhance my goal.md", "optimize this goal", or sharing a goal.md file and…
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
cmux-architecture
Skill "cmux-architecture" from manaflow-ai/cmux, covering cmux architecture, package architecture, layers, file organization and documentation.