library-of-context AGENTS.md

library-of-context AGENTS.md is an instructions file for Codex, OpenCode from hwillGIT/library-of-context. It costs 680 tokens per session, scanned A, original, MIT.

Repository instructions for writing technical prose in the library-of-context project. They require clear, present-tense explanations with specialized terms defined at first use.

In plain words
What is it for?
They are for guiding documentation, examples, help text, comments, and other technical writing in that repository.
Why use it?
They help keep project documentation understandable, consistent, and focused on system behavior rather than the editing process.

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/hwillgit/library-of-context/agents-md
Clone the repo
git clone --depth 1 https://github.com/hwillGIT/library-of-context

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 library-of-context AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hwillgit/library-of-context/agents-md.svg)](https://agentmods.dev/instructions/hwillgit/library-of-context/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hwillgit/library-of-context/agents-md"><img src="https://agentmods.dev/badge/instructions/hwillgit/library-of-context/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 680 This file is loaded in full into every session.
When invoked 680 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 $0.00680 $0.00680
Opus 5 $0.00340 $0.00340
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 3d ago against content hash b47d125f24d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

library-of-context 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository instructions

Technical prose

Every development agent must read and apply the timeless technical prose skill before it creates, edits, reviews, or summarizes documentation. This requirement also applies to examples, help text, docstrings, and code comments.

Write explanatory material in one editorial present. Describe behavior, interfaces, constraints, failure modes, and operational reasons. State the complete contract directly.

Do not narrate the prompt, requester, author choices, drafting process, refactoring process, or edit sequence. Do not state when explanatory content entered the repository relative to other content.

Use active voice and American spelling. Limit descriptive sentences to 25 words. Limit procedural sentences to 20 words. Put one instruction in each procedural sentence. Do not use contractions or semicolons. Limit each paragraph to six sentences and one topic.

Define a specialized term or acronym at its first use. Use plain technical English. Replace vague or promotional language with the mechanism, condition, and effect.

For dense engineering or concurrency text, name the component that performs each action. Replace noun stacks with subject-verb-object sentences. Preserve ownership, operation order, atomic boundaries, locks, transactions, failure behavior, and resource limits.

When a user supplies a passage for translation, structure the response in two parts:

  1. Part 1: Plain-English Translation contains one or two direct sentences.
  2. Part 2: Key Concepts Explained contains bullets that define the necessary terms.

When editing a repository document, keep its document structure. Put the direct translation in the main text. Define key concepts at first use or in the glossary.

For pull request summaries, reviews, commit messages, and GitHub Actions text, read .agents/skills/write-timeless-technical-prose/references/github-technical-communication.yaml. State the failure risk, mechanical fix, and guaranteed state in that order. Preserve the exact lock, transaction, data-store, ordering, and isolation guarantees.

Read the full file on GitHub · 68 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. 3d ago First seen · 68 lines · 680 tokens per session scan A b47d125f24d8

Subscribe to this mod's changes

library-of-context AGENTS.md is an instructions file published in the GitHub repository hwillGIT/library-of-context (0 stars, last pushed 13d ago), licensed MIT. It adds 680 tokens to every session, about $0.0034 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.