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-secretsgit 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-secrets)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-secrets"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-secrets/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-secrets"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-secrets.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 | $0.00031 | $0.01113 |
| Opus 5.5 | $0.00012 | $0.00445 |
| Sonnet 5.5 | $0.00006 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
mainframe-secrets 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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Credential handling
Use the installed credential mechanism without bringing protected values into model-visible commands or output.
Resolve the credential
- Use existing native authentication or a credential reference already resolved
in the current task when sufficient. Read
{{CREDENTIALS_INDEX}}when a credential identity, delivery route, or catalog entry needs resolution. - If a required catalog lookup is unresolved or unavailable, return the exact missing catalog configuration to your immediate caller. Do not search unrelated locations or initialize a replacement catalog.
- Treat the catalog as metadata only: service identities, addresses, credential names, access commands, and non-secret operational notes.
- Never read, search, print, summarize, diff, or archive the protected credential store.
- Do not use
mainframe-secret listfor routine discovery. Use the catalog. - Do not infer authority to perform an external action merely because a credential exists.
Deliver the value to a consumer
Prefer an already configured native mechanism such as an SSH agent, gh
authentication, a system credential service, or a consumer-owned credential
file.
When the consumer accepts an environment variable, prefer process-scoped delivery:
mainframe-secret run REGISTERED_NAME -- consumer-command
This exposes only the requested registered names to that child process. Do not load the complete store from shell startup files.
If the consumer requires a value in a specific input and no safer native,
environment, or stdin mechanism exists, nest mainframe-secret get REGISTERED_NAME
directly inside that single consumer invocation. Never run mainframe-secret get as a
standalone inspection command.
Never manually echo, log, serialize, retain, or place a value in a response, prompt, ticket, URL, commit, patch, manifest, telemetry event, diagnostic trace, model-authored shell variable, or temporary file. Avoid process arguments when a safer delivery channel exists. Never weaken TLS, certificate, or SSH host-key verification to make authentication succeed.
What ships with it
1 file 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.
- 10d ago Changed · +2 tokens per session 25d60943ea5d
- 15d ago Changed · +12 lines · -51 tokens per session 6d90d760412f
- 1mo ago Changed · +64 lines · +20 tokens per session a220df9aadb6
- 1mo ago First seen · 52 lines · 60 tokens per session scan A 774e9bd1e791
mainframe-secrets is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 1,113 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 2026-08-31.
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.