t1-t2-protocol: Instructions file for Codex

AGENTS.md

t1-t2-protocol AGENTS.md is an instructions file for Codex, OpenCode from Fauxetine/t1-t2-protocol. It costs 453 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a server that provides three reasoning tools: T1 protocol, T2 protocol, and checksum. T1 breaks down unclear questions, T2 evaluates answers, and checksum checks a required format.

In plain words
What is it for?
They are for handling ambiguous questions, reviewing answer confidence, checking structured responses, and guiding caller-side fact verification.
Why use it?
They tell an agent which reasoning step to use, in what order, and when outside web research is needed for changing facts.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Fauxetine/t1-t2-protocol's own configuration. It tells Codex and OpenCode how to work on t1-t2-protocol itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything t1-t2-protocol configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Fauxetine/t1-t2-protocol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Fauxetine/t1-t2-protocol/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Fauxetine/t1-t2-protocol

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for t1-t2-protocol AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fauxetine/t1-t2-protocol/agents-md.svg)](https://agentmods.dev/instructions/fauxetine/t1-t2-protocol/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/fauxetine/t1-t2-protocol/agents-md"><img src="https://agentmods.dev/badge/instructions/fauxetine/t1-t2-protocol/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 453 This file is loaded in full into every session.
When invoked 453 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00453 $0.00453
Opus 5 $0.00227 $0.00227
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00045 $0.00045

Measured 6d ago against content hash ed6d99a74c3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

t1-t2-protocol 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 6d 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 · 32 lines

What it actually says

Agent instructions (MCP hosts)

This repository ships an stdio MCP server with three tools: t1_protocol, t2_protocol, and checksum.

  1. t1_protocol — when the user question is ambiguous; decompose into L1–L4 tiers first.
  2. checksum — before T2 when the answer must follow structural format ([L1…] sections + trailing ---).
  3. t2_protocol — evaluate confidence and adoption recommendations from a different model than the producer when possible.

Caller-side web verification (v2.6)

The server has no network access. If the topic involves time-sensitive facts (library status, prices, recent events), search on the caller side first, then call t2_protocol. See docs/caller-protocol.md.

Parameters

Tool Key args Notes
t1_protocol question, optional weight_hint, locale locale: en (default) or zh
t2_protocol answer, optional weight_hint, locale Same weights as T1
checksum text Returns JSON (checksum_passed, errors); deterministic, stdlib-only

Weight hints (English or Chinese): fact-first / 事实优先, efficiency-first / 效率优先, cost-first / 成本优先, robustness-first / 鲁棒性优先, general-first / 通用优先.

t1_protocol and t2_protocol return prompt templates for the host LLM. Only checksum returns structured JSON.

Constraints for contributors and agents

  • Keep src/t1_t2_mcp_server.py stdlib-only (Layer 0).
  • Do not add web search, pip dependencies, or network I/O to the MCP server.
  • Prefer extending caller-side rules/docs over bloating the server.
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. 6d ago First seen · 32 lines · 453 tokens per session scan A ed6d99a74c3e

Subscribe to this mod's changes

t1-t2-protocol AGENTS.md is an instructions file published in the GitHub repository Fauxetine/t1-t2-protocol (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 453 tokens to every session, about $0.0023 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

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

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

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).

microsoft/vscode · 6,785 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

langchain AGENTS.md

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 · 4,469 tokens

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.

github/spec-kit · 7,104 tokens