agentmods.dev

escalation

escalation is a skill for Claude Code from nikolamin/claude-coordinator-kit. It costs 43 tokens per session (326 once invoked), scanned A, original, MIT.

A set of rules for asking a separate advice-focused agent for help after repeated attempts fail or an architecture decision remains unclear.

In plain words
What is it for?
Use it after the allowed retry cycles are exhausted, for unresolved design or architecture questions, and for a second opinion on research or copywriting work.
Why use it?
It prevents endless retries and gives difficult problems a fresh review with the previous attempts and blocker explained.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the coordinator-kit plugin — 15 skills, 1 hook shipped together

not rated 2repo changed 1mo ago A scan 43 tokens original MIT

Good fit Use it after the allowed retry cycles are exhausted, for unresolved design or architecture questions, and for a second opinion on research or copywriting work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nikolamin/claude-coordinator-kit/escalation
View source ↗ nikolamin/claude-coordinator-kit
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.

Any agent
npx skills add nikolamin/claude-coordinator-kit --skill escalation
Clone the repo
git clone --depth 1 https://github.com/nikolamin/claude-coordinator-kit

Made for: Claude Code.

Or install coordinator-kit, the plugin that ships this one along with the rest of its 15 skills, 1 hook.

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 escalation

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/escalation/github.svg)](https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/escalation)
Your own site
<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/escalation"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/escalation/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 escalation

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikolamin/claude-coordinator-kit/escalation"><img src="https://agentmods.dev/badge/skills/nikolamin/claude-coordinator-kit/escalation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 326 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 $0.00043 $0.00326
Opus 5.5 $0.00017 $0.00130
Sonnet 5.5 $0.00009 $0.00065
Haiku 4.5 $0.00004 $0.00033

Measured 1mo ago against content hash f28612e61a77, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

escalation 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 1mo 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.

plugins/coordinator-kit/skills/escalation/SKILL.md · 27 lines

What it actually says

Escalation

After the initial failure and two failed fix/re-verify cycles on the same gap, stop repeating that approach. Dispatch a fresh advice-tier agent using the project's recorded model alias. Supply original criteria, failure evidence, attempted fixes and constraints; ask what mechanism was missed and what to try next. Routine first failures do not need an escalation. A changed agent id does not reset the gap's counter.

For UI/UX, copy, research and document review, an available differently-trained opinion can expose shared blind spots. Use coordinator-kit:codex-second-opinion from within the dispatched agent when applicable. Preserve the project's explicit model/effort preference and confirm the configured model is supported by the installed runtime. If unavailable, proceed with the available review and record the limitation once. Engineering-only plumbing does not automatically need it.

The advice agent returns options and evidence, not production permission. The coordinator chooses within existing authority or presents the concrete founder-only decision through coordinator-kit:question-protocol; keep independent lanes moving.

Infra/execution briefs include: "Do not delegate; execute directly. Bulk output goes to the named project scratch log; return decisive lines, counts, exit codes and evidence paths." See coordinator-kit:agent-brief-hygiene for the complete bounded-work contract.

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. 1mo ago Changed · -23 lines · -273 tokens per session f28612e61a77
  2. 2mo ago Changed · +5 lines · +4 tokens per session 6d6dc0a23d7a
  3. 2mo ago First seen · 45 lines · 312 tokens per session scan A 021e1525fd4d

Subscribe to this mod's changes

escalation is a skill published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 29d ago), licensed MIT. It adds 43 tokens to every session and 326 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents
Related

escalation compared with skills from other repositories

escalation next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
escalationnikolamin/claude-coordinator-kitSkill229d agoMITA43Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex