escalate

escalate is a command for Claude Code from EZotoff/ez-omo-config. It costs 17 tokens per session (276 once invoked), scanned A, original, MIT.

A decision-escalation command that asks three independent judge agents for a verdict when a choice is blocked. It reports the vote, confidence, strongest argument, and dissent, but the operator can still overrule it.

In plain words
What is it for?
It is for difficult technical or project decisions where the options, evidence, and reason for being stuck can be presented to an independent panel.
Why use it?
It provides a defined way to move past persistent disagreement or uncertainty without pretending the evidence is stronger than it is. Low-confidence votes can result in a request for more evidence instead of a forced choice.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit It is for difficult technical or project decisions where the options, evidence, and reason for being stuck can be presented to an independent panel.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ezotoff/ez-omo-config/escalate
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/EZotoff/ez-omo-config

Made for: Claude Code.

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 escalate

README.md
[![agentmods](https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/escalate.svg)](https://agentmods.dev/commands/ezotoff/ez-omo-config/escalate)
Your own site
<a href="https://agentmods.dev/commands/ezotoff/ez-omo-config/escalate"><img src="https://agentmods.dev/badge/commands/ezotoff/ez-omo-config/escalate.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 276 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 $0.00017 $0.00276
Opus 5 $0.00009 $0.00138
Sonnet 5 $0.00003 $0.00055
Haiku 4.5 $0.00002 $0.00028

Measured yesterday against content hash 5709141428e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

escalate 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.

commands/escalate.md · 14 lines

What it actually says

Escalate the blocked decision to a three-judge panel for a binding verdict. Input: the decision, the options, and why it's stuck (disagreement, uncertainty, or competing priorities).

Panel: three judge agents in independent sessions, different model families where available. Each receives the same case file — decision, options, evidence, and the specific question to answer — and returns: verdict (choose one option / send back for more work), confidence (0–1), and the single argument that most drove their verdict.

Tally: 3–0 or 2–1 → report the verdict and the dissenting argument in full (a strong dissent is a warning label on a 2–1). Any judge below 0.6 confidence → their vote counts as abstain; 2 abstains = "insufficient basis — here's what evidence the judges asked for".

Boundary: the verdict binds the ANALYSIS, not the operator — report it with the dissent and stop. The operator may overrule; if they do, record the override and the reason (that recording is how the presets get calibrated later).

After the verdict, note in one line: what would have to be true for this decision to have been safe to make without escalation at all.

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 · 14 lines · 17 tokens per session scan A 5709141428e8

Subscribe to this mod's changes

escalate is a command published in the GitHub repository EZotoff/ez-omo-config (5 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 276 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 2026-09-06.