touchstone AGENTS.md

Repository instructions for Touchstone, a project that develops and tests its own review and methodology tools.

In plain words
What is it for?
Use them when working on Touchstone’s methodology, external-review wrappers, classifier, installation script, or related tests.
Why use it?
They prevent contributors from skipping the required methodology and identify the checks that must stay passing when review scripts or installation code change.

Instructions file for CodexOpenCode

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/devdacian/touchstone/agents-md
Clone the repo
git clone --depth 1 https://github.com/devdacian/touchstone

Made for: Codex, OpenCode.

Per session 270 This file is loaded in full into every session.
When invoked 270 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.

ModelPer sessionOnce invoked
Fable 5 $0.00270 $0.00270
Opus 5 $0.00135 $0.00135
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 2d ago against content hash c5dd261a0bf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

touchstone AGENTS.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 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.

AGENTS.md · 23 lines

What it actually says

Codex entry (Touchstone source repo)

This repo develops Touchstone and dogfoods it on itself; the methodology lives under .touchstone/methodology/.

Before any skill / methodology / Touchstone / consult / review-loop / external-review work, FIRST read .touchstone/methodology/TOUCHSTONE.md — the COMPLETE runtime-neutral process, self-sufficient for a Codex orchestrator (it includes the pinned reverse cross-model wrapper for running a Claude reviewer). Under Claude Code, ALSO read .touchstone/methodology/TOUCHSTONE-claude.md for the Claude-specific mechanisms.

This repo's own dogfood tests for the external-review machinery live in tests/external-review/ (NOT under .touchstone/methodology/, so they are never vendored into hosts). When you change the classifier or wrappers under .touchstone/methodology/scripts/external-review/, run and keep them green: bash tests/external-review/test-classifier.sh and bash tests/external-review/test-forward-wrapper-argv.sh and bash tests/external-review/test-reverse-wrapper-argv.sh.

When you change install.sh, run and keep green: bash -n install.sh and bash tests/test-install-output.sh.

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.

  1. 2d ago First seen · 23 lines · 270 tokens per session scan A c5dd261a0bf8

Subscribe to this mod's changes

touchstone AGENTS.md is an instructions file published in the GitHub repository devdacian/touchstone (19 stars, last pushed 1mo ago), licensed MIT. It adds 270 tokens to every session, about $0.0014 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit 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.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens