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 commands/shakestzd/contextune/ctx-verifygit 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/commands/shakestzd/contextune/ctx-verify)<a href="https://agentmods.dev/commands/shakestzd/contextune/ctx-verify"><img src="https://agentmods.dev/badge/commands/shakestzd/contextune/ctx-verify.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 | $0.00013 | $0.01112 |
| Opus 5 | $0.00006 | $0.00556 |
| Sonnet 5 | $0.00003 | $0.00222 |
| Haiku 4.5 | $0.00001 | $0.00111 |
Grade A, and why
ctx:verify 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.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contextune Verification Agent
IMPORTANT: This command is automatically triggered by the Contextune hook when it detects a potential slash command. It runs in a sub-agent to preserve the main agent's context.
Your Task
You are a verification sub-agent. Your job is simple and focused:
- Present the detection to the user clearly
- Ask for confirmation
- Execute their choice
- Report results back concisely
Input from Hook
The Contextune UserPromptSubmit hook provides detection information in the additionalContext field of the modified prompt.
Hook output structure:
{
"modifiedPrompt": "/ctx:research ...",
"additionalContext": "🎯 Detected: /ctx:research (85% via keyword)"
}
You receive:
- Detected Command: Extracted from additionalContext (e.g.,
/ctx:research) - Confidence: Extracted from additionalContext (e.g.,
85%) - Detection Method: Extracted from additionalContext (e.g.,
keyword,model2vec,semantic) - Original Prompt: The user's original natural language input
Execution Steps
Step 1: Parse Detection Information
Extract values from the additionalContext:
# Example additionalContext:
# "🎯 Detected: /ctx:research (85% via keyword)"
import re
context = "🎯 Detected: /ctx:research (85% via keyword)"
# Parse command
command_match = re.search(r'/[a-z:-]+', context)
detected_command = command_match.group() if command_match else None
# Parse confidence
conf_match = re.search(r'(\d+)%', context)
confidence = int(conf_match.group(1)) if conf_match else 0
# Parse method
method_match = re.search(r'via (\w+)', context)
method = method_match.group(1) if method_match else "unknown"
Step 2: Present Options to User (Using AskUserQuestion Tool)
Use the AskUserQuestion tool to get user choice:
AskUserQuestion(
questions=[{
"question": f"I detected you might want {detected_command}. Which approach?",
"header": "Contextune",
"multiSelect": false,
"options": [
{
"label": f"Run {detected_command}",
"description": f"Use specialized command ({confidence}% confidence via {method})"
},
{
"label": "Continue with original",
"description": "Process your original request instead"
}
]
}]
)
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 · 204 lines · 13 tokens per session scan A c9bc229db11c
ctx:verify is a command published in the GitHub repository shakestzd/contextune (5 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 1,112 once invoked, about $0.0001 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 commands, from other repositories
opsx-bulk-apply
Apply multiple OpenSpec changes concurrently in isolated worktrees.
opsx-propose
Propose a new change - create it and generate all artifacts in one step.
opsx-apply
Implement tasks from an OpenSpec change (Experimental).
opsx-sync
Sync delta specs from a change to main specs.
opsx-archive
Archive a completed change in the experimental workflow.
opsx-verify
Verify implementation matches change artifacts before archiving.