deadeye-mute

deadeye-mute is a command for Claude Code from deepaksinghcs14/deadeye-cc. It costs 18 tokens per session (199 once invoked), scanned A, original, MIT.

A session command that silences deadeye's advisories, workflow hints, and plan reminders.

In plain words
What is it for?
Use it to mute deadeye guidance temporarily, or run it with “off” to restore the messages.
Why use it?
It removes these interruptions when they are not useful for the current session, while leaving hard plan requirements in force.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the deadeye plugin — 10 skills, 3 commands, 7 hooks shipped together

Good fit Use it to mute deadeye guidance temporarily, or run it with “off” to restore the messages.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/deepaksinghcs14/deadeye-cc/deadeye-mute
Install

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.

Clone the repo
git clone --depth 1 https://github.com/deepaksinghcs14/deadeye-cc

Made for: Claude Code.

Or install deadeye, the plugin that ships this one along with the rest of its 10 skills, 3 commands, 7 hooks.

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 deadeye-mute

README.md
[![agentmods](https://agentmods.dev/badge/commands/deepaksinghcs14/deadeye-cc/deadeye-mute/github.svg)](https://agentmods.dev/commands/deepaksinghcs14/deadeye-cc/deadeye-mute)
Your own site
<a href="https://agentmods.dev/commands/deepaksinghcs14/deadeye-cc/deadeye-mute"><img src="https://agentmods.dev/badge/commands/deepaksinghcs14/deadeye-cc/deadeye-mute/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 deadeye-mute

Your own site · 80×15
<a href="https://agentmods.dev/commands/deepaksinghcs14/deadeye-cc/deadeye-mute"><img src="https://agentmods.dev/badge/commands/deepaksinghcs14/deadeye-cc/deadeye-mute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 199 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00018 $0.00199
Opus 5 $0.00009 $0.00100
Sonnet 5 $0.00004 $0.00040
Haiku 4.5 $0.00002 $0.00020

Measured 9d ago against content hash 48cfe0a20296, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deadeye-mute 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 9d 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.

commands/deadeye-mute.md · 19 lines

What it actually says

The deadeye daemon handles this command itself through its prompt hook — you don't need to run anything. Relay the confirmation line that appears in your hook context (DEADEYE MUTED / DEADEYE UNMUTED) to the user.

If no confirmation appeared in context, the daemon likely isn't running; tell the user any tool call will respawn it and they can try again.

Muting is session-scoped and silences nags only: advisories (repeat reads/commands, large files, unbounded dumps, Grep limits), soft plan-gate suggestions, and workflow hints. Silent Bash output rewrites keep saving tokens, a plan_gate: hard setting keeps enforcing, and the coder persona stays governed by /deadeye-coder. /deadeye-mute off restores everything.

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. 9d ago First seen · 19 lines · 18 tokens per session scan A 48cfe0a20296

Subscribe to this mod's changes

deadeye-mute is a command published in the GitHub repository deepaksinghcs14/deadeye-cc (5 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 199 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.