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 instructions/wasintoh/toh-framework/claude-mdgit clone --depth 1 https://github.com/wasintoh/toh-frameworkWrote 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/wasintoh/toh-framework/claude-md)<a href="https://agentmods.dev/instructions/wasintoh/toh-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/wasintoh/toh-framework/claude-md.svg" alt="Measured on agentmods" 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 | $0.03979 | $0.03979 |
| Opus 5 | $0.01989 | $0.01989 |
| Sonnet 5 | $0.00796 | $0.00796 |
| Haiku 4.5 | $0.00398 | $0.00398 |
Grade A, and why
toh-framework 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 today.
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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Toh Framework (repo development guide)
Guide for a Claude Code agent developing the framework itself. Repo-only: not in the package.json
files whitelist, so it never ships to npm. (claude-code.js generates a separate, unrelated CLAUDE.md inside end-user projects.)
What this is
Toh Framework ("Type Once, Have it all") is the npm package toh-framework (v2.2.0, MIT, ESM,
Node >= 18, no build step) that installs an AI-orchestration development system into 6 IDEs:
Claude Code, Cursor (2.4+), Antigravity (agy CLI + IDE), Codex (CLI + desktop app), ZCode (Z.ai), and —
Enterprise-only, behind --legacy-gemini — Gemini CLI (consumer service shut down 2026-06-18).
North Star: a non-technical person types one sentence, approves once ("Go"), and THE TOH LOOP builds, tests, and fixes a real, beautiful app until verified DONE. Quality is measured at the END USER's experience; any added question or step is a regression — /toh-vibe asks zero questions, /toh-plan asks exactly one.
Everyday commands
All npm scripts wrap node bin/toh-cli.js <cmd>, which lazy-loads installer/*.js:
npm run install:local— interactive installer;-- --quick(plus-t <dir>) for non-interactive runs (dir must pre-exist; reinstalls still prompt). Flags:--legacy-gemini,--legacy-cursorrules.npm run uninstall:local— the counterpart;-- -t <dir> --dry-runto preview,--yesfor scripts,--allto also delete .toh/plan.md + .toh/progress.md + both memory folders. Defaults to cwd, so ALWAYS pass-twhen testing.npm run list— print the catalog, live-read from src/ frontmatter (throws on bad YAML)npm run status— inspect install state (~/.claude, ./.toh, manifest.json)npm run bundle— web prompt bundles into ./dist/web-bundlesnpm pack --dry-run— check exactly what ships before any packaging change
Verification protocol
npm test runs tests/codex.test.js (node:test, in-band via tests/run.js; TOH_QUIET=1 silences ora) —
it covers the Codex surfaces only. Everything else is still verified by running for real:
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.
- today Changed · +6 lines · +161 tokens per session c9ef5571a044
- 4d ago First seen · 189 lines · 3,818 tokens per session scan A ef933b37e4e7
toh-framework CLAUDE.md is an instructions file published in the GitHub repository wasintoh/toh-framework (95 stars, last pushed yesterday), licensed MIT. It adds 3,979 tokens to every session, about $0.0199 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.
Other instructions, from other repositories
earnings-edge CLAUDE.md
Claude Code instructions for suhaas/earnings-edge, covering earnings-edge: project memory for claude code, architecture & core concepts, the graph, agent roles and tools & skills boundary.
python-instructions
Rules for all Python files: strict typing, async-first, error wrapping, imports organization, no print(). Use when: modifying src/ files, adding agents, tools, or utility functions.
flow-nexus CLAUDE.md
Claude Code instructions for ruvnet/flow-nexus, covering claude code configuration - sparc development environment, 🚨 critical: concurrent execution & file management, ⚡ golden rule: "1 message = all related operations", 🎯 critical: claude code task tool for agent execution and 📁 file organization rules.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.