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/shakestzd/contextune/claude-mdgit clone --depth 1 https://github.com/shakestzd/contextuneWrote 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/shakestzd/contextune/claude-md)<a href="https://agentmods.dev/instructions/shakestzd/contextune/claude-md"><img src="https://agentmods.dev/badge/instructions/shakestzd/contextune/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 | $0.04921 | $0.04921 |
| Opus 5 | $0.02461 | $0.02461 |
| Sonnet 5 | $0.00984 | $0.00984 |
| Haiku 4.5 | $0.00492 | $0.00492 |
Grade B, and why
contextune CLAUDE.md scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- ❌ DON'T: Execute arbitrary code How it starts
The opening of the file, as written. The whole thing — 744 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contextune Development Guide
Project Overview
Contextune is a Claude Code plugin that provides natural language to slash command mapping. It uses a 3-tier detection cascade (keyword → Model2Vec → Semantic Router) to detect user intent and suggest appropriate slash commands.
Core Technology:
- Python 3.10+ with UV for dependency management
- Claude Code plugin architecture (hooks system)
- Machine learning: Model2Vec embeddings + Semantic Router
- Documentation: MkDocs with mkdocstrings
Critical Development Rules
Versioning
Version Increment Rule:
- ALL version changes increment by 0.0.1 (patch level only)
- Current: 0.8.3 → Next: 0.8.4 → After: 0.8.5
- NO major/minor bumps (0.9.0, 1.0.0, etc.)
Files to Update:
.claude-plugin/plugin.json-versionfield.claude-plugin/marketplace.json-versionfield (marketplace and plugin entry)- Update both files in same commit
Example:
// .claude-plugin/plugin.json
{
"version": "0.8.4" // Was 0.8.3
}
// .claude-plugin/marketplace.json
{
"version": "0.8.4", // Marketplace version
"plugins": [{
"version": "0.8.4" // Plugin version
}]
}
Package Management - UV Only
ALWAYS use UV for Python operations:
# Run scripts
uv run script.py
# Run with dependencies
uv run --with pytest pytest
# Add dependencies
uv add package-name
# Add dev dependencies
uv add --dev package-name
# Sync environment
uv sync
# Run module
uv run -m pytest
NEVER use:
pip install- useuv addpython script.py- useuv run script.pypoetryorconda- UV only
UV Script Format (PEP 723)
All standalone scripts MUST use inline script metadata:
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "model2vec>=0.3.0",
# "numpy>=1.24.0"
# ]
# ///
# Script code here
Why: UV automatically creates ephemeral venvs with correct dependencies. This is how Claude Code hooks work.
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 · 744 lines · 4,921 tokens per session scan B d4d4485a4875
contextune CLAUDE.md is an instructions file published in the GitHub repository shakestzd/contextune (5 stars, last pushed 8mo ago), licensed MIT. It adds 4,921 tokens to every session, about $0.0246 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
intent-driven-template AGENTS.md
Instructions for intent-driven-dev/intent-driven-template, a project described as: OpenSpec and OpenCode template for intent-driven development with specs, ADRs, C4 diagrams, Gherkin, TDD, Multi-Model Adversarial Spec Authoring, Glossary for Domain Terms, and reusable engineering workflows. This also makes OpenSpec…
navigator CLAUDE.md
Claude Code instructions for alekspetrov/navigator, covering navigator: finish what you start, why this exists, core principle, navigator runtime (v7) and session start.
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
apm python.instructions.md
Python development guidelines.
ai-agents security.instructions.md
Instructions for rjmurillo/ai-agents, covering security file rules, must, should, must not and references.
claude-plugins CLAUDE.md
Claude Code instructions for aiocean/claude-plugins, covering claude.md, what this is, plugin structure, marketplace registry and plugin categories.