What is mainframe CLAUDE.md?

A repository guide for Mainframe, a Bash-based toolkit that gives AI coding agents shared memory, structured output, safety helpers, and a list of available functions across several coding tools.

Use it when an AI agent needs to work on Mainframe or follow its conventions through tools such as Claude Code, OpenAI Codex, Cursor, or Aider.

It gives agents consistent instructions about supported platforms, libraries, patterns, and JSON handling instead of making them infer how the repository works.

mainframe CLAUDE.md — Instructions file by gtwatts

Install

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.

agentmods

npx agentmods add instructions/gtwatts/mainframe/claude-md

Clone the repo

git clone --depth 1 https://github.com/gtwatts/mainframe

Per session 1,466 This file is loaded in full into every session.

When invoked 1,466 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01466	$0.01466
Opus 5	$0.00733	$0.00733
Sonnet 5	$0.00293	$0.00293
Haiku 4.5	$0.00147	$0.00147

Measured 3d ago against content hash 394469d4b16f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mainframe CLAUDE.md 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 3d 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.

CLAUDE.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MAINFRAME - AI Coding Assistant Instructions

Bash runtime for AI agents with persistent working memory, structured output, safety primitives, and a generated function registry.

source "${MAINFRAME_ROOT:-$HOME/.mainframe}/lib/common.sh"

Platform Support

Platform	Integration	Status
Pi	`skills/pi/SKILL.md` + Pi MAINFRAME tools	Instructions + tools
Claude Code	`skills/claude-code/SKILL.md`	Instructions
OpenAI Codex / Codex CLI	`skills/codex/AGENTS.md`	Instructions
Kimi Code CLI	`skills/kimi-cli/SKILL.md`	Instructions
Google CLI	`skills/google-cli/SKILL.md`	Instructions
OpenCode	`skills/opencode/SKILL.md`	Instructions
Cursor	`.cursorrules` / `skills/cursor/`	Instructions
Aider	`skills/aider/CONVENTIONS.md`	Instructions
Vercel AI SDK	`skills/vercel-ai-sdk/`	System-prompt template
Custom Agents	stable-core broker + separately installed `mainframe-mcp`	Reviewed adapter

Library Overview

Category	Libraries	Key Functions
Core	strings, arrays, json, files, utils, ansi	`json_object`, `array_join`, `trim_string`, `uuid`
Data	datetime, http, csv, git, crypto, semver	`now_iso`, `http_get`, `csv_to_json`, `sha256`
System	proc, path, env, docker, sysinfo, compat	`proc_find_by_port`, `path_join`, `docker_exec`
Validation	validation, regex	`validate_email`, `sanitize_html`, `regex_match`
AI Agent	idempotent, atomic, observe, context, diff, cache, agent, awm, orchestrate	`ensure_dir`, `atomic_write`, `diff_replace`, `orch_agent_spawn`
CLI	anim, tui, output, stream	`spinner_start`, `progress_bar`, `output_success`
GitHub	github, github_actions, github_security	`gh_pr_create`, `gha_workflow_run`, `ghs_score`
Cloud	ext/aws, ext/gcp, ext/k8s	`aws_s3_list`, `k8s_pods` (optional, requires CLI)

Read the full file on GitHub · 151 lines

Changes

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.

3d ago First seen · 151 lines · 1,466 tokens per session scan A 394469d4b16f

Subscribe to this mod's changes

mainframe CLAUDE.md is an instructions file published in the GitHub repository gtwatts/mainframe (11 stars, last pushed 4d ago), licensed MIT. It adds 1,466 tokens to every session, about $0.0073 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 2026-08-30.

Building agents Memory and context automation bash bash-library cli developer-tools linux

mainframe CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

MAINFRAME - AI Coding Assistant Instructions

Platform Support

Library Overview

What this file has done since we first saw it

Other instructions, from other repositories

warp AGENTS.md

best-claude-hud AGENTS.md

OpenDeck AGENTS.md

mcp-screenshot-server CLAUDE.md

headson CLAUDE.md

typetype AGENTS.md