evo-route-doctor

evo-route-doctor is a skill for Claude Code, Codex from ZekaiShi/evo-subagent. It costs 41 tokens per session (306 once invoked), scanned A, original, MIT.

A troubleshooting guide for finding why a child agent uses the wrong model or fails before starting in DeepSeek Harness. It checks workspace files, model registrations, routing choices, and prompts without changing settings.

In plain words
What is it for?
Use it to diagnose provider, model, workspace-binding, template, and prompt problems for a specific agent key. It can also show when a route could not be verified because the live model list is unavailable.
Why use it?
It replaces guesswork when an agent inherits an unexpected route or has an invalid provider-and-model pairing. It reports the first failed check and the smallest correction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to diagnose provider, model, workspace-binding, template, and prompt problems for a specific agent key. It can also show when a route could not be verified because the live model list is unavailable.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zekaishi/evo-subagent/evo-route-doctor
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 ZekaiShi/evo-subagent --skill evo-route-doctor
Clone the repo
git clone --depth 1 https://github.com/ZekaiShi/evo-subagent

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 evo-route-doctor

README.md
[![agentmods](https://agentmods.dev/badge/skills/zekaishi/evo-subagent/evo-route-doctor/github.svg)](https://agentmods.dev/skills/zekaishi/evo-subagent/evo-route-doctor)
Your own site
<a href="https://agentmods.dev/skills/zekaishi/evo-subagent/evo-route-doctor"><img src="https://agentmods.dev/badge/skills/zekaishi/evo-subagent/evo-route-doctor/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 evo-route-doctor

Your own site · 80×15
<a href="https://agentmods.dev/skills/zekaishi/evo-subagent/evo-route-doctor"><img src="https://agentmods.dev/badge/skills/zekaishi/evo-subagent/evo-route-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 306 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 $0.00041 $0.00306
Opus 5.5 $0.00016 $0.00122
Sonnet 5 $0.00008 $0.00061
Haiku 4.5 $0.00004 $0.00031

Measured today against content hash 0aa469b202b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-28, from the pricing page.

Security

Grade A, and why

evo-route-doctor 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 today.

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/evo-route-doctor/SKILL.md · 16 lines

What it actually says

Evo route doctor

Find the route selected for a specific agent_key and explain it from the current workspace and registered DSH models.

  1. Identify the conversation workspace and the exact agent_key. Inspect <workspace>/agents/<agent_key>.md; if absent, check whether it is one of the plugin's bundled templates (code-reviewer, researcher, wps-worker). An unknown key inherits the parent route.
  2. For a binding or template, check the strict four-line header: ---, provider: <id>, model: <id>, ---. Compare both IDs, including case, with the models registered in this DSH session. The plugin rejects an unregistered pair before starting a child.
  3. Check whether the caller supplied a nonempty prompt. For a built-in role, that replaces its bundled role prompt; a workspace copy uses its local role body only when the caller's prompt is empty.
  4. Report the observed route, the file or inheritance path that selected it, the first failing check, and the smallest correction. If the live registry is unavailable, say that registration remains unverified.

Keep diagnosis read-only unless the user asks to change a binding. Do not print credentials or infer a model from its display name.

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. today First seen · 16 lines · 41 tokens per session scan A 0aa469b202b1

Subscribe to this mod's changes

evo-route-doctor is a skill published in the GitHub repository ZekaiShi/evo-subagent (7 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 306 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 2026-09-28.

Related

Other skills, from other repositories

diagnosing-bugs-zh

A diagnostic workflow for difficult bugs and performance regressions, meaning cases where software behaves incorrectly or becomes slower after a change.

gongyijie85/mattpocock-skills-dsh-zh · 48 tokens

dsh-hooks-authoring

Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.

KYinCode/dsh-hooks-plugin · 112 tokens

error-handling

Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages. Use when designing error types, retries, circuit breakers, or user-facing failure messages in TypeScript, Python, or Go.

gongyijie85/dsh-ecc · 61 tokens

kubernetes-patterns

Kubernetes workload patterns, resource management, RBAC, probes, autoscaling, ConfigMap/Secret handling, and kubectl debugging for production-grade deployments. Use when writing or reviewing Kubernetes manifests, or debugging probes, RBAC, autoscaling, or resource limits.

gongyijie85/dsh-ecc · 58 tokens

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications…

gongyijie85/dsh-ecc · 95 tokens

click-path-audit

Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any…

gongyijie85/dsh-ecc · 71 tokens