CATWILLgh/MAINFRAME

Agent-agnostic instructions, skills, agents, commands, and hooks adapted natively to coding-agent environments.

This repository also configures its own agents. See what MAINFRAME tells them →

2Stars on the repository
30Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

CATWILLgh/MAINFRAME

Skill Codex

Run bounded HTTP(S) requests with curl when no narrower client can provide the needed evidence.

not rated 2 changed 14d ago C 25 tokens copy · 89% MIT

mainframe-frontend

02

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Design, implement, debug, or review React web interfaces, including forms, browser state, accessibility, and interaction tests. Not React Native or standalone design systems.

not rated 2 changed 9d ago A 37 tokens copy · 91% MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Plan, diagnose, change, or verify project infrastructure: deployment, CI/CD, containers, networking, TLS, storage, and recovery. Not application implementation.

not rated 2 changed 8d ago A 36 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Start, restart, or stop local application servers, managed services, or Compose stacks while identifying processes, ports, and ownership. Not one-shot commands.

not rated 2 changed 9d ago A 39 tokens copy · 94% MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Design, implement, debug, or review Python web services, APIs, and workers, including async lifecycle, persistence, and backend tests. Not data science or ML pipelines.

not rated 2 changed 9d ago A 40 tokens original MIT

mainframe-secrets

06

CATWILLgh/MAINFRAME

Skill Codex

Resolve credential identities, deliver secrets to a process, or administer entries through the MAINFRAME credential index and helper, without exposing values.

not rated 2 changed 9d ago A 31 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Design, implement, debug, or review Node.js TypeScript services and Next.js server layers, including APIs, Server Actions, persistence, workers, and backend tests.

not rated 2 changed 9d ago A 40 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Assess a consequential decision or readiness claim when mistaken acceptance could cause material harm, such as a production rollout, migration, or recovery. Not routine code review.

not rated 2 changed 9d ago A 38 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Record an observed MAINFRAME or agent-harness fault, including missing skills, broken hooks, conflicting instructions, or adapter failures. Not application bug reports.

not rated 2 changed 9d ago A 36 tokens original MIT

mainframe-peer-work

10

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Use an external coding-agent CLI only when the user or project agreement explicitly assigns that product work.

not rated 2 changed 14d ago A 24 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Audit or repair project agent configuration when instructions conflict, skills are missing, or hooks, permissions, and tool policies misbehave. Not a routine setup check.

not rated 2 changed 9d ago A 38 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Preserve unresolved project findings as structured tickets during ordinary work; establish a local ticket queue when none exists. Not an audit campaign or a way to defer unfinished work.

not rated 2 changed 8d ago A 40 tokens original MIT

mainframe-research

13

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Resolve dependent, disputed, or consequential external claims through authoritative sources, including compatibility comparisons and conflicting documentation. Not routine single-fact lookups.

not rated 2 changed 9d ago A 33 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Assess existing tests and CI when their quality is questioned, regressions escape, checks are flaky or costly, or green results are misleading. Read-only audit; use mainframe-testing to write, run, or repair checks.

not rated 2 changed 9d ago A 50 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Design, implement, debug, or review Go services, APIs, and workers, including transactions, concurrency, retries, and backend tests.

not rated 2 changed 9d ago A 33 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Plan, query, integrate, or troubleshoot ClickHouse, including query cost, ingestion, schema changes, deletion, and recovery across production, shared test, and disposable targets.

not rated 2 3d ago A 39 tokens original MIT

mainframe-k3s

17

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Plan, install, troubleshoot, secure, upgrade, or recover K3s clusters, including topology, networking, storage, and datastore backups. Not application-only changes or other Kubernetes distributions.

not rated 2 3d ago A 43 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Implement, adapt, or troubleshoot Keycloak OIDC login in a web application, including an admin connection screen, group-to-role mapping, account linking, and session lifecycle. Not Keycloak server deployment or login-page theming alone.

not rated 2 3d ago A 53 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Implement or troubleshoot application notifications and their settings UI, event routing, templates and delivery through Bitrix24, Telegram, webhooks, email or Web Push. Not one-off message sending, chat UI toasts or messaging-server deployment alone.

not rated 2 3d ago A 52 tokens original MIT

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Design, implement or repair an application's System/Diagnostics page with service health, resource metrics, logs and optional scoped container controls or data previews. Use for embedded operational consoles and misleading diagnostic states; not standalone monitoring-platform deployment or one-off infrastructure…

not rated 2 3d ago A 55 tokens original MIT

mainframe-testing

21

CATWILLgh/MAINFRAME

Skill Claude CodeCodex

Design, write, run, or repair tests and GitHub/GitLab CI during development. Use for test strategy, TDD, analysis tools, fixtures, local/CI boundaries, and verification evidence. Use mainframe-test-audit to assess an existing test system.

not rated 2 3d ago A 58 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: