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.
npx agentmods add instructions/hwillgit/library-of-context/agents-mdgit clone --depth 1 https://github.com/hwillGIT/library-of-contextWrote 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.
[](https://agentmods.dev/instructions/hwillgit/library-of-context/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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:
Part 1: Plain-English Translationcontains one or two direct sentences.Part 2: Key Concepts Explainedcontains 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.
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.
- 3d ago First seen · 68 lines · 680 tokens per session scan A b47d125f24d8
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.
Other instructions, from other repositories
codex-image-context-runtime AGENTS.md
Instructions for shixinnt/codex-image-context-runtime, covering agents.md, public boundary, runtime contract and changes.
snapshot-mcp-server CLAUDE.md
Claude Code instructions for WhenMoon-afk/snapshot-mcp-server, covering claude.md, project overview, development commands, build & run and package & installation.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
barkeep AGENTS.md
AGENTS.md instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
CrewClaw AGENTS.md
Instructions for staruhub/CrewClaw, covering agents.md, project, boundaries (charter, 2026-07-10), commands and employee package rules.