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/gtwatts/mainframe/opencodenpx skills add gtwatts/mainframe --skill opencodegit clone --depth 1 https://github.com/gtwatts/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 | $0.00022 | $0.03080 |
| Opus 5 | $0.00011 | $0.01540 |
| Sonnet 5 | $0.00004 | $0.00616 |
| Haiku 4.5 | $0.00002 | $0.00308 |
Grade C, and why
mainframe scanned grade C with 1 finding 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 yesterday.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- MAINFRAME-HOST-CONTRACT {"schema_version":1,"contract_version":"1.3.0","registry":"config/host-capabilities.json","registry_sha256":"0b4a8b98161b5caddf7a2ebdfd26d1c2b8f0a8967fbbf89818cdf2ed4b1e3fc5","host":"opencode This is a copy
94% identical to mainframe — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruction evidence: instructions only. Runtime configuration, enforcement, live use, and release status are platform-bound in config/host-capabilities.json; unsupported routes remain unverified.
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.
- yesterday First seen · 87 lines · 22 tokens per session scan C f06ef45ab1c3
mainframe is a skill published in the GitHub repository gtwatts/mainframe (11 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 3,080 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). It is 94% identical to mainframe, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
gui-onboarding-verification-skill
GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
gui-integration-test
GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…
gui-settings-ui
GUI desktop app only. How to build a Settings page in the Warp client (app/src/settingsview) so its widgets and settings search behave correctly — picking a PageType, deciding whether a heading belongs in the page-title slot or inside a widget, gating a widget, and scoping searchterms per widget. Use when adding or…
logging-and-error-reporting
How and when to log (log:: levels, safe macros) and report errors to Sentry (reporterror!) in the Warp codebase. Use when adding or reviewing any logging or error reporting — picking a log level, deciding log vs. reporterror!, keeping sensitive data out of logs, or surfacing an error to Sentry.