outside-voice

outside-voice is a skill for Claude Code, Codex from drvoss/everything-copilot-cli. It costs 35 tokens per session (1,108 once invoked), scanned A, original, MIT.

An independent second opinion that challenges a plan, helps investigate a blocker, or reviews completed work. It uses a direct, practical perspective to create distance from the current approach.

In plain words
What is it for?
Use it before implementation, during debugging or design work, or after a change is complete and you want an independent review.
Why use it?
It helps expose hidden assumptions, missed constraints, and safer alternatives before a decision is locked in. It can also identify problems when work appears finished.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/drvoss/everything-copilot-cli/outside-voice
Any agent
npx skills add drvoss/everything-copilot-cli --skill outside-voice
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli

Made for: Claude Code, Codex.

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 outside-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/outside-voice.svg)](https://agentmods.dev/skills/drvoss/everything-copilot-cli/outside-voice)
Your own site
<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/outside-voice"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/outside-voice.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,108 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.01108
Opus 5 $0.00017 $0.00554
Sonnet 5 $0.00007 $0.00222
Haiku 4.5 $0.00003 $0.00111

Measured yesterday against content hash 2e0f6bcf2c12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

outside-voice 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 yesterday.

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.

skills/workflow/outside-voice/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outside Voice

Outside Voice creates deliberate distance from your current momentum. Instead of continuing to push the same plan, it asks a second opinion to challenge the framing, pressure-test the approach, or review the result in a blunt, useful voice:

Direct, concrete, builder-to-builder. No filler.

When to Use

  • A plan feels plausible, but you want a strong preflight challenge before implementation
  • You are in the middle of debugging or design work and need an outside perspective on the blocker
  • A change is "done" but you want an independent review before calling it complete
  • The conversation has become anchored on one approach and you want a fresh take

When NOT to Use

Instead of outside-voice Use
Broad multi-path decision-making with multiple roles council
Formal code/security review against a concrete diff code-review or pr-security-review
Choosing the cheapest or strongest model for a task multi-model-strategy

Modes

Mode Trigger Output
challenge Before implementation starts A critique of the plan, missing constraints, safer alternatives
consult During active work A narrow outside view on the blocker, assumption, or stuck point
review After implementation A verdict on correctness, risk, and what still needs work

Workflow

1. Pick the mode explicitly

State the exact role up front:

Use outside-voice in challenge mode.
We have not started implementation yet.
Critique the approach before we commit to it.

2. Pass only the artifact that needs judgment

Do not dump the whole session. Give the outside voice a compact target:

  • challenge -> proposed plan, acceptance criteria, constraints
  • consult -> blocker, current hypothesis, relevant files or logs
  • review -> diff summary, test status, known risks

The smaller the artifact, the easier it is to stay independent from your original framing.

Read the full file on GitHub · 169 lines

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. yesterday First seen · 169 lines · 35 tokens per session scan A 2e0f6bcf2c12

Subscribe to this mod's changes

outside-voice is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 1,108 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

winui-design

Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…

microsoft/win-dev-skills · 119 tokens

winui-dev-workflow

Build and run workflow for WinUI 3 apps with WinApp CLI 0.6+ — project creation with winapp new, project-mode winapp run, BuildAndRun.ps1 analyzer integration, crash diagnosis, and prerequisites. Use when creating, building, running, or fixing build errors in a WinUI 3 project.

microsoft/win-dev-skills · 73 tokens

winui-packaging

MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…

microsoft/win-dev-skills · 86 tokens

winui-session-report

Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.

microsoft/win-dev-skills · 61 tokens

microsoft-build

Your companion for Microsoft Build 2026. Helps you find sessions relevant to your project, discover what's new for your tech stack, scaffold projects from sessions, and plan your event schedule. Activate when users mention sessions, schedule, what's new, Build, Ignite, AI Tour, Microsoft event, conference, or…

microsoft/Build-CLI · 109 tokens

git-tidy

Comprehensive git repository hygiene in one pass: local and remote branches, worktrees, stashes, tags, remotes, merge and rebase artifacts, ignored-but-tracked files, large history blobs, and maintenance health. Every finding is classified by confidence (safe, review, keep) and nothing is deleted without explicit…

jongio/skills · 145 tokens