agentmods.dev

context-os: Instructions file for Claude Code

CLAUDE.md

context-os CLAUDE.md is an instructions file for Claude Code from jacob-dietle/context-os. It costs 675 tokens per session, scanned A, original, MIT.

Guided instructions for building a shared knowledge system where agents turn notes and documents into connected, reusable information.

In plain words
What is it for?
Use them to set up the system, import transcripts or notes, inspect the knowledge structure, ground decisions, evaluate progress, and plan work across multiple agents.
Why use it?
They help organize accumulated project knowledge and reveal missing context before work begins.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is jacob-dietle/context-os's own configuration. It tells Claude Code how to work on context-os 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 context-os configures →

not rated 115repo +1 2mo ago A scan 675 tokens original MIT
View source ↗ jacob-dietle/context-os
Reuse

Borrowing it

Nothing to install: this file belongs to jacob-dietle/context-os. 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/jacob-dietle/context-os/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jacob-dietle/context-os

Made for: Claude Code.

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 context-os CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jacob-dietle/context-os/claude-md/github.svg)](https://agentmods.dev/instructions/jacob-dietle/context-os/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jacob-dietle/context-os/claude-md"><img src="https://agentmods.dev/badge/instructions/jacob-dietle/context-os/claude-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 context-os CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jacob-dietle/context-os/claude-md"><img src="https://agentmods.dev/badge/instructions/jacob-dietle/context-os/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 675 This file is loaded in full into every session.
When invoked 675 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 $0.00675 $0.00675
Opus 5.5 $0.00270 $0.00270
Sonnet 5.5 $0.00135 $0.00135
Haiku 4.5 $0.00068 $0.00068

Measured 2mo ago against content hash 4b7aa7c4f45f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-os CLAUDE.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.

CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GTM Context OS Quickstart

Purpose: Help users build their first context operating system in 10 minutes.

What This Plugin Does

Provides guided setup for creating a Context OS — a structured knowledge graph where AI compounds intelligence over time. The system uses stigmergic coordination: agents read and modify the shared environment, knowledge compounds through use.

Skills

Claude Code discovers and fires these based on intent — no slash commands needed.

Skill When it fires
quickstart User wants 10-minute guided setup of a new Context OS
ingest User wants raw content (transcripts, docs, notes) turned into knowledge nodes
context-os-basics Foundation patterns for Context OS
context-os-cli Query work context, file activity, heat metrics, and graph structure
context-gap-analysis Check what already exists before building
epistemic-context-grounding Ground decisions in domain knowledge before designing
eval-loop Iterate systematically toward a quality target with automated backpressure
coordinated-agent-teams Decompose a spec into a multi-agent implementation plan

Quick Start

Say "run the quickstart" to begin — the quickstart skill fires. The guide will:

  1. Ask what your context OS is for (GTM, Product, Research)
  2. Create the two-layer directory structure (knowledge graph + operational docs)
  3. Generate CLAUDE.md navigation guide with context-os CLI commands
  4. Process your first piece of content into a structured knowledge node
  5. Verify it works

Total time: ~10 minutes

How Context OS Works

Two-Layer Architecture

Knowledge Graph (knowledge_base/)

  • Atomic, reusable concepts with frontmatter metadata
  • Linked via [[wiki-links]] — the graph has structure
  • Lifecycle: emergent → validated (2+ citations) → canonical

Operational Docs (00_foundation/)

  • Strategic documents that compose from the graph
  • They reference atomic concepts, they don't redefine them

Read the full file on GitHub · 89 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 · 89 lines · 675 tokens per session scan A 4b7aa7c4f45f

Subscribe to this mod's changes

context-os CLAUDE.md is an instructions file published in the GitHub repository jacob-dietle/context-os (115 stars, last pushed 2mo ago), licensed MIT. It adds 675 tokens to every session, about $0.0027 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.

Memory and context
Related

context-os CLAUDE.md compared with instructions from other repositories

context-os CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
context-os CLAUDE.mdjacob-dietle/context-osInstructions file1152mo agoMITA675Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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