escalation-router

escalation-router is an agent for Claude Code from ivegamsft/basecoat. It costs 43 tokens per session (545 once invoked), scanned A, original, MIT.

A routing agent that sends high-risk or irreversible decisions to an appropriate human approver and records the decision in GitHub.

In plain words
What is it for?
It is for release signoff, compliance gates, irreversible changes, and ambiguous decisions connected to a pull request.
Why use it?
It prevents routine automation from making decisions that need human judgment and preserves a review trail.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit It is for release signoff, compliance gates, irreversible changes, and ambiguous decisions connected to a pull request.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-escalation-router
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/ivegamsft/basecoat

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 escalation-router

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-escalation-router/github.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-escalation-router)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-escalation-router"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-escalation-router/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-router

Your own site · 80×15
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-escalation-router"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-escalation-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 545 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 $0.00545
Opus 5 $0.00022 $0.00272
Sonnet 5 $0.00009 $0.00109
Haiku 4.5 $0.00004 $0.00055

Measured 5d ago against content hash 6d7b7c038e13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

escalation-router 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 5d 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.

agents/basecoat-10-core-escalation-router.agent.md · 60 lines

What it actually says

Escalation Router Agent

Purpose: route high-risk decisions to the right human approver, package the decision in a structured template, and preserve the approval trail in GitHub.

Inputs

  • The decision or change that needs approval
  • Repository and PR context, if available
  • The identified risk trigger and why automation should stop
  • The approver role or owner, if already known

Workflow

  1. Classify — decide if the request is high-risk, irreversible, ambiguous, or policy-sensitive; skip routine work.
  2. Select the approver and state why that person owns the decision.
  3. Build the packet using the skills/escalation-routing/references/approval-packet-template.md schema: decision type, risk level, approver, recommendation, options considered, blocking conditions, next action.
  4. Publish the PR comment path — if tied to a PR, ask for a threaded reply per the template below.
  5. Record the decision — capture the human's outcome and next action in the GitHub trail.
  6. Degrade gracefully — if no approver is available, mark deferred and list the exact blocker.

Routing Rules

  • Route to a human for data loss, production risk, compliance exposure, or ambiguous release decisions, or when tradeoffs can't be encoded safely in automation.
  • Never auto-approve after a timeout, and never hide the decision in a vague "looks good" comment.

PR-Comment Approval Path & Decision Template

See agents/references/escalation-router-detail.md for the PR-comment posting workflow and the full decision template.

Output Format

escalation_router_result:
  status: "ROUTED | DEFERRED | CLOSED"
  approver: "<human name or role>"
  risk_level: "medium | high | critical"
  decision_packet:
    id: "<unique-id>"
    recommendation: "<approve | approve_with_conditions | reject | defer>"
    pr_comment_url: "<url | null>"
    next_action: "<what happens next>"
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. 5d ago Changed · -49 lines 6d7b7c038e13
  2. 9d ago First seen · 109 lines · 43 tokens per session scan A 7c2ac1047a3f

Subscribe to this mod's changes

escalation-router is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 545 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 2026-08-31.

Related

Other agents, from other repositories

keel

Designs processes, SOPs, OKR cascades, vendor contracts, and compliance programs that scale with company growth. Use when documenting a business process, auditing ops posture, or managing vendor contracts. Trigger with "write a SOP", "build our OKR framework".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

Recruitment Specialist

Expert recruitment operations and talent acquisition specialist — skilled in China's major hiring platforms, talent assessment frameworks, and labor law compliance. Helps companies efficiently attract, screen, and retain top talent while building a competitive employer brand.

SHAdd0WTAka/Zen-Ai-Pentest · 46 tokens

enforcement-strategy-advisor

Expert in behavioral change psychology for software teams, enforcement strategy design, and SDLC adoption coaching. Use for designing enforcement approaches, managing resistance to standards, adapting strategies to team maturity, and turning compl...

SteveGJones/ai-first-sdlc-practices · 47 tokens

launch-watcher

Monitors the launch tracker (Jira/Linear) for upcoming launches that likely need legal review, flags them before product counsel gets surprised. Runs daily. Trigger: "what launches are coming", "what should I know about", "launch radar", or on schedule.

zhou210712/claude-for-legal-ZH · 58 tokens

ip-renewal-watcher

Scheduled agent that reads the IP portfolio register, computes what's due, and posts a ranked deadline report. Runs weekly by default. Posts to the channel named in /.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md → Renewal alerts. Trigger phrases: "what's renewing", "IP deadlines", "portfolio check", "IP…

ZekaiSuni/claude-for-legal-turkish · 89 tokens

dataroom-watcher

Sanal Veri Odasını (VDR) yeni yüklenen belgeler için izler ve planlanan zamanda kapanış kontrol listesinin durumunu paylaşır. Yüksek öncelikli kategorilerle (Örn: KVKK, Rekabet, Ticari Sözleşmeler) eşleşen yeni yüklemeleri işaretler. Tetikleyici: "veri odasında yeni ne var", "VDR güncellemeleri" veya planlanmış zaman.

ZekaiSuni/claude-for-legal-turkish · 102 tokens