Borrowing it
Nothing to install: this file belongs to gtwatts/mainframe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gtwatts/mainframe/main/CLAUDE.mdgit clone --depth 1 https://github.com/gtwatts/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/instructions/gtwatts/mainframe/claude-md)<a href="https://agentmods.dev/instructions/gtwatts/mainframe/claude-md"><img src="https://agentmods.dev/badge/instructions/gtwatts/mainframe/claude-md/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/instructions/gtwatts/mainframe/claude-md"><img src="https://agentmods.dev/badge/instructions/gtwatts/mainframe/claude-md.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 | $0.01466 | $0.01466 |
| Opus 5.5 | $0.00586 | $0.00586 |
| Sonnet 5.5 | $0.00293 | $0.00293 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
mainframe CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAINFRAME - AI Coding Assistant Instructions
Bash runtime for AI agents with persistent working memory, structured output, safety primitives, and a generated function registry.
source "${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) |
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.
- 2mo ago First seen · 151 lines · 1,466 tokens per session scan A 394469d4b16f
mainframe CLAUDE.md is an instructions file published in the GitHub repository gtwatts/mainframe (12 stars, last pushed 25d ago), licensed MIT. It adds 1,466 tokens to every session, about $0.0059 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 2026-08-30.
mainframe CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mainframe CLAUDE.mdgtwatts/mainframe | Instructions file | 12 | 25d ago | MIT | A | 1,466 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |