LLM-Wiki: Instructions file for Codex

AGENTS.md

LLM-Wiki AGENTS.md is an instructions file for Codex, OpenCode from TrueHOOHA/LLM-Wiki. It costs 4,245 tokens per session, scanned A, original, Apache-2.0.

A project instruction file defining the format and maintenance rules for LLM-Wiki, a structured knowledge base made of linked documents. It describes the document types, required metadata, directory layout, and project mission.

In plain words
What is it for?
Use it when creating, editing, checking, or organizing documents in the wiki, including entities, concepts, sources, and summaries.
Why use it?
It tells agents how to add or update knowledge without breaking the wiki's format or losing links between related concepts.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions OpenCode.

This is TrueHOOHA/LLM-Wiki's own configuration. It tells Codex and OpenCode how to work on LLM-Wiki 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 LLM-Wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TrueHOOHA/LLM-Wiki. 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/TrueHOOHA/LLM-Wiki/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/TrueHOOHA/LLM-Wiki

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 LLM-Wiki AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/truehooha/llm-wiki/agents-md/github.svg)](https://agentmods.dev/instructions/truehooha/llm-wiki/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/truehooha/llm-wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/truehooha/llm-wiki/agents-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.

agentmods 80×15 button for LLM-Wiki AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/truehooha/llm-wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/truehooha/llm-wiki/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,245 This file is loaded in full into every session.
When invoked 4,245 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 $0.04245 $0.04245
Opus 5.5 $0.01698 $0.01698
Sonnet 5.5 $0.00849 $0.00849
Haiku 4.5 $0.00424 $0.00424

Measured 2mo ago against content hash 270c8dcd6c34, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LLM-Wiki 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 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.

AGENTS.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Wiki Schema

This is the authoritative schema document. The LLM must follow these conventions when maintaining the wiki. Treat this as the system prompt for wiki operations.

Mission

Build and maintain a persistent, compounding knowledge base. The wiki is not a dump of raw text—it is a structured, interlinked artifact that grows richer with every source. Cross-references are pre-built. Contradictions are flagged. Synthesis reflects everything read so far.

OKF Conformance

The wiki/ tree is an Open Knowledge Format (OKF) bundle (v0.1). wiki/ is the bundle root; every .md file under it that is not a reserved filename (index.md, log.md) is an OKF concept document. Files outside wiki/ (AGENTS.md, README.md, SPEC.md, raw/**) are project-level artifacts, not part of the bundle, and are not subject to OKF conformance.

OKF (SPEC.md §9) requires only that every concept document carry a parseable YAML frontmatter block with a non-empty type field, and that reserved files follow §6/§7. This document defines the producer conventions layered on top of OKF: the four type values used (entity, concept, source, synthesis), their recommended sections, the cross-link and citation style, and the index/log contracts. These are permitted OKF extensions (SPEC.md §4.1 Extensions, §4.2 body). Where this document is silent, OKF (SPEC.md) governs.

Obsidian-first deviation from OKF §5. OKF §5 recommends standard markdown links for cross-linking. This bundle instead uses Obsidian wikilinks ([[note]]) for all internal note-to-note links, to provide first-class Obsidian graph-view support. Link format is not an OKF §9 conformance requirement, and OKF's permissive consumption model (§9) tolerates this. External URLs remain standard markdown links ([text](https://…)) — wikilinks are for internal notes only.

Non-negotiables

  1. Raw sources are immutable. The LLM never edits files in raw/. Ever.
  2. The LLM owns the wiki layer. All markdown files under wiki/ are created, updated, and maintained by the LLM unless explicitly overridden by the operator.
  3. Every action is logged. Every ingest, query result filed, and lint pass appends an entry to wiki/log.md.
  4. The index is always current. wiki/index.md must reflect the state of the wiki after every operation that touches pages.
  5. Cross-references are first-class. Every page should link to related pages. Orphan pages are bugs.

Read the full file on GitHub · 306 lines

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. 2mo ago First seen · 306 lines · 4,245 tokens per session scan A 270c8dcd6c34

Subscribe to this mod's changes

LLM-Wiki AGENTS.md is an instructions file published in the GitHub repository TrueHOOHA/LLM-Wiki (22 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 4,245 tokens to every session, about $0.0170 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.

Related

LLM-Wiki AGENTS.md compared with instructions from other repositories

LLM-Wiki AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
LLM-Wiki AGENTS.mdTrueHOOHA/LLM-WikiInstructions file223mo agoApache-2.0A4,245Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode