knowledge-trust-core AGENTS.md

knowledge-trust-core AGENTS.md is an instructions file for Codex, OpenCode from haorantang97/knowledge-trust-core. It costs 164 tokens per session, scanned A, original, MIT.

Repository instructions for a read-only trust-policy core: software that evaluates the reliability or maturity of knowledge using evidence. They define boundaries for changing the repository.

In plain words
What is it for?
Use them when modifying this repository to preserve deterministic, explainable verdicts, stable reason codes, synthetic examples, and its read-only scope.
Why use it?
They prevent contributors from adding unrelated capabilities, weakening trust rules, or storing private material. They also require tests and verification before behavior changes.

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/haorantang97/knowledge-trust-core/agents-md
Clone the repo
git clone --depth 1 https://github.com/haorantang97/knowledge-trust-core

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 knowledge-trust-core AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/haorantang97/knowledge-trust-core/agents-md.svg)](https://agentmods.dev/instructions/haorantang97/knowledge-trust-core/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/haorantang97/knowledge-trust-core/agents-md"><img src="https://agentmods.dev/badge/instructions/haorantang97/knowledge-trust-core/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 164 This file is loaded in full into every session.
When invoked 164 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 $0.00164 $0.00164
Opus 5 $0.00082 $0.00082
Sonnet 5 $0.00033 $0.00033
Haiku 4.5 $0.00016 $0.00016

Measured 3d ago against content hash e3f16962632f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-trust-core 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 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.

AGENTS.md · 12 lines

What it actually says

Agent contribution rules

This repository is a read-only trust-policy core. Preserve that boundary.

  • Add a failing test before every behavior change and run npm run verify before completion.
  • Keep verdicts deterministic, versioned, and explainable with stable reason codes.
  • Do not add numeric truth scores. Maturity is a bounded evidence state, not probability.
  • Do not add storage, retrieval, vector search, approval, Git mutation, database, shell, or network tools to the core or MCP server.
  • Do not silently weaken knowledge-trust-default; weaker variants require a distinct policy ID.
  • Never commit real notes, Raw material, personal paths, credentials, databases, or private source excerpts. Examples must remain synthetic.
  • Adapters may normalize explicit syntax but must not infer missing trust values.
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. 3d ago First seen · 12 lines · 164 tokens per session scan A e3f16962632f

Subscribe to this mod's changes

knowledge-trust-core AGENTS.md is an instructions file published in the GitHub repository haorantang97/knowledge-trust-core (0 stars, last pushed 9d ago), licensed MIT. It adds 164 tokens to every session, about $0.0008 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

llm-wiki-agent AGENTS.md

AGENTS.md instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.

SamurAIGPT/llm-wiki-agent · 2,349 tokens

llm-wiki-agent CLAUDE.md

Claude Code instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, slash commands (claude code), directory layout, page format and ingest workflow.

SamurAIGPT/llm-wiki-agent · 2,038 tokens

llm-wiki-agent GEMINI.md

Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.

SamurAIGPT/llm-wiki-agent · 1,590 tokens

llm-wiki-compiler AGENTS.md

AGENTS.md instructions for atomicstrata/llm-wiki-compiler, covering llmwiki, development guidelines, code style & standards, clean code rules and comments and documentation.

atomicstrata/llm-wiki-compiler · 713 tokens

hippocampus CLAUDE.md

Instructions for sturlese/hippocampus, covering layout, frontmatter schema, conventions, answering questions from the vault (read order) and contradictions.

sturlese/hippocampus · 1,570 tokens

hippocampus AGENTS.md

Instructions for sturlese/hippocampus: Read and follow CLAUDE.md in the repository root completely before doing any work. It is the canonical project contract, written for Claude Code as the native host; its vault rules and workflows apply unchanged to Codex.

sturlese/hippocampus · 54 tokens