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/frontendnpx skills add CATWILLgh/MAINFRAME --skill frontendgit 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 | $0.00045 | $0.01580 |
| Opus 5 | $0.00023 | $0.00790 |
| Sonnet 5 | $0.00009 | $0.00316 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade A, and why
frontend scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- mainframe-frontend — 91% identical, 53 lines differ
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend engineering
Deliver one coherent user-facing result. Treat React implementation, interaction quality, visual design, accessibility, component reuse, and focused tests as branches of the same frontend task rather than independent products.
Establish the active frontend
- Run the recon helper as
node "${CLAUDE_SKILL_DIR}/scripts/recon.js" <package-root>, or follow manual recon, before choosing an approach. - Trace the changed user journey through its route, component tree, state, browser boundary, server contract, visible states, and existing tests.
- Preserve the installed framework, rendering model, router, architecture, state, validation, styling, primitives, and visual language unless their migration or redesign is explicitly part of the task.
- Verify installed versions and version-sensitive APIs with Context7 or current primary documentation.
- Complete the assigned behavior. Do not use TODOs, placeholders, disabled or weakened checks, suppressions, or deferred in-scope work as a substitute for implementing it.
Several routers, state libraries, validators, or UI systems are observations, not automatic blockers. Resolve the active owner from imports, providers, configuration, runtime wiring, and affected files. Escalate only an unresolved choice that changes product behavior, infrastructure, permission, or the assigned visual direction.
Route only the relevant context
React and browser engineering
| Changed concern | Read |
|---|---|
| Framework, rendering, routing, Server and Client Components | frameworks |
| Module ownership and established architecture | architecture |
| Fetching, mutations, caching, and optimistic UI | data fetching |
| Forms and validation | forms |
| PWA, IndexedDB, offline queues, and realtime | offline and realtime |
| Editors, Markdown, files, tables, charts, and complex interaction | content and data UI |
| Browser trust boundaries, secrets, XSS, and version-sensitive styling | safety |
| Logic, component, browser, and CI test scope | testing |
What ships with it
30 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.
- references/accessibility.md 3.0 KB
- references/architecture.md 1.4 KB
- references/color.md 2.8 KB
- references/content-and-data-ui.md 2.4 KB
- references/data-fetching.md 1.6 KB
- references/design-context.md 2.2 KB
- references/design-workflows.md 2.5 KB
- references/distinctiveness.md 3.6 KB
- references/flows-and-feedback.md 945 B
- references/forms.md 1.5 KB
- references/frameworks.md 1.5 KB
- references/layout.md 1.9 KB
- references/mode-experience.md 883 B
- references/mode-operate.md 879 B
- references/mode-persuade.md 878 B
- references/mode-read.md 811 B
- references/motion.md 2.2 KB
- references/offline-and-realtime.md 1.5 KB
- references/recon.md 1.4 KB
- references/review-and-evidence.md 2.2 KB
- references/safety.md 1.7 KB
- references/shadcn-cli.md 1.5 KB
- references/shadcn-component-map.md 1.1 KB
- references/shadcn-composition.md 1.8 KB
- references/shadcn-forms.md 1.2 KB
- references/testing.md 2.6 KB
- references/type-craft.md 2.7 KB
- references/typography.md 2.3 KB
- scripts/inspect-ui.mjs 2.8 KB runs code
- scripts/recon.js 5.0 KB runs code
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 · 132 lines · 45 tokens per session scan A c8760defe3da
frontend is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 11d ago), licensed MIT. It adds 45 tokens to every session and 1,580 once invoked, about $0.0002 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.