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/johnnichev/nv-context/claude-mdgit clone --depth 1 https://github.com/johnnichev/nv-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/johnnichev/nv-context/claude-md)<a href="https://agentmods.dev/instructions/johnnichev/nv-context/claude-md"><img src="https://agentmods.dev/badge/instructions/johnnichev/nv-context/claude-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 | $0.00248 | $0.00248 |
| Opus 5 | $0.00124 | $0.00124 |
| Sonnet 5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
nv-context 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 4d 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.
What it actually says
Claude-Specific: nv-context
@AGENTS.md @docs/MANIFESTO.md @docs/HIERARCHY-OF-LEVERAGE.md @docs/FAQ.md
Session Management
When context gets heavy (~40 messages or after exploring research/):
- Update HANDOFF.md with current progress
/clear- Start fresh: "Read HANDOFF.md and continue where I left off"
This outperforms auto-compaction. At 60% context = safe. At 70% = precision drops. At 85% = hallucinations start. Compact proactively.
Compounding Engineering
When you make a mistake a rule could have prevented:
- Fix the mistake
- Add one line to AGENTS.md that prevents it
- The codebase gets smarter with every session
Claude-Specific
- SKILL.md is the product. Treat every edit like editing a prompt worth $1000.
- Use
wc -lafter every SKILL.md edit. The 500-line budget is a hard constraint, not a guideline. - Research logs are excluded via .claudeignore. Read research/SYNTHESIS.md for the distilled version.
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.
- 4d ago First seen · 29 lines · 248 tokens per session scan A 2228556a96ed
nv-context CLAUDE.md is an instructions file published in the GitHub repository johnnichev/nv-context (7 stars, last pushed 4mo ago), licensed MIT. It adds 248 tokens to every session, about $0.0012 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
harness-engineering CLAUDE.md
Instructions for jrenaldi79/harness-engineering, covering claude.md, project overview, core features, essential commands and testing.
vibe-27 AGENTS.md
AGENTS.md instructions for fatalex27/vibe-27, covering vibe-27 behavioral guidelines, 1. editor, not typist, 2. intention over implementation, 3. trust and verify and 4. think before coding.
AIWiki CLAUDE.md
Claude Code instructions for XuebinMa/AIWiki, covering claude.md — aiwiki 项目记忆, 这是什么, 每次动手前必读（按顺序）, 写作 / 翻译用 skill（不要手搓流程） and 保持连贯的硬规则（防止跨会话的风格 / 内容漂移）.
ai-context-hierarchy CLAUDE.md
Instructions for CreatmanCEO/ai-context-hierarchy, covering ai-context-hierarchy — claude.md (level 1), status: active, architecture, critical rules — when editing this repo and commands.
agent-context-doctor AGENTS.md
AGENTS.md instructions for dadion123/agent-context-doctor, covering agent notes, commands, product direction and maintainer workflow.
lynxprompt-vscode CLAUDE.md
Claude Code instructions for GeiserX/lynxprompt-vscode, covering claude.md — lynxprompt vs code, tech stack, development, architecture and key commands.