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.
curl -O https://raw.githubusercontent.com/jacob-dietle/context-os/main/.claude/skills/context-os-basics/SKILL.mdgit clone --depth 1 https://github.com/jacob-dietle/context-osWrote 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/skills/jacob-dietle/context-os/context-os-basics)<a href="https://agentmods.dev/skills/jacob-dietle/context-os/context-os-basics"><img src="https://agentmods.dev/badge/skills/jacob-dietle/context-os/context-os-basics/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.
<a href="https://agentmods.dev/skills/jacob-dietle/context-os/context-os-basics"><img src="https://agentmods.dev/badge/skills/jacob-dietle/context-os/context-os-basics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00012 | $0.00656 |
| Opus 5.5 | $0.00005 | $0.00262 |
| Sonnet 5.5 | $0.00002 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
context-os-basics 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context OS Basics
What is a Context OS?
A context operating system is a structured knowledge system where:
- AI compounds intelligence over time (never re-teach)
- Knowledge persists across sessions
- Concepts link to each other (graph, not files)
- Two layers separate reusable knowledge from operational docs
The Two-Layer Architecture
Layer 1: Atomic Knowledge Graph (knowledge_base/)
Individual reusable concepts:
- Technical knowledge
- Business insights
- Methodologies and patterns
Each node:
- Has structured frontmatter (metadata)
- Links to related concepts via [[wiki-links]]
- Follows lifecycle: emergent → validated → canonical
Layer 2: Operational Documents (00_foundation/)
Strategic artifacts that COMPOSE Layer 1:
- Positioning documents
- Messaging frameworks
- Process documentation
Key principle: Operational docs REFERENCE atomic concepts, they don't redefine them.
Constitutional Documents
taxonomy.yaml
Defines blessed tags for your system:
- Domains (technical, business, methodology)
- Node types (concept, pattern, case-study)
- Status values (emergent, validated, canonical)
- Your custom topic library
Start small. Add tags only after 3+ nodes demonstrate need.
ontology.yaml
Defines how concepts relate:
- Relationship types (enables, supports, implements)
- Linking requirements (minimum links per node)
- Quality thresholds
Evidence-Based Attribution
Every claim needs a source:
- [VERIFIED: file:line] - Direct evidence
- [INFERRED: logic] - Deduced from evidence
- [UNVERIFIABLE] - Cannot confirm (be honest)
Quality standard: If you can't cite a source, don't claim it.
The 4-Phase Framework (Summary)
- Reconnaissance - Understand domain and requirements
- Architecture - Design two-layer structure
- Construction - Build knowledge graph and ops docs
- Validation - Test and document system
Key Anti-Patterns
1. One Continuous Thread
Problem: Single long conversation without writing to files Fix: Write intermediate results to files, preserve attribution chains
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.
- 2mo ago First seen · 109 lines · 12 tokens per session scan A 58d0bb99a461
context-os-basics is a skill published in the GitHub repository jacob-dietle/context-os (115 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 656 once invoked, about $0.0000 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.
context-os-basics compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| context-os-basicsjacob-dietle/context-os | Skill | 115 | 2mo ago | MIT | A | 12 | Claude Code |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |