Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/understudylabs/understudy-agent-toolsnpx agentmods add skills/understudylabs/understudy-agent-tools/check-routing-healthWrote 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.
[](https://agentmods.dev/skills/understudylabs/understudy-agent-tools/check-routing-health)<a href="https://agentmods.dev/skills/understudylabs/understudy-agent-tools/check-routing-health"><img src="https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/check-routing-health/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.
<a href="https://agentmods.dev/skills/understudylabs/understudy-agent-tools/check-routing-health"><img src="https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/check-routing-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 3 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 16 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.02057 |
| Opus 5 | $0.00043 | $0.01028 |
| Sonnet 5 | $0.00017 | $0.00411 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
check-routing-health 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Routing Health
Use this worker when the developer wants to know whether Understudy routing is causing errors, which workloads are routed, whether a declared route is really taking effect, or where their gateway usage and spend goes. These are read-only hosted endpoints that answer "is this us?" without asking the team.
Checked against existing skills: use-understudy-gateway owns auth, routing
setup, and route writes; ramp-and-verify owns production traffic changes.
This skill owns read-only diagnostic queries against the reporting surface and
does not write routes or change traffic.
Safety Gates
These endpoints are read-only and carry no side effects. They do not change
routes, traffic percentages, or provider configuration. Do not print the full
sk_* key in output — mask it to the last 4 characters. Prefer the first-class
understudy reporting commands, which resolve the signed-in organization and
project without exposing credentials to a child process.
Vocabulary — use these words, exactly
Everything you say to the user must use the canonical routing vocabulary:
- Route outcomes (
route_shares):primary— the customer-requested model was served (includes catalog-by-name);understudy— an Understudy-configured route moved the traffic;fallback— a recovery re-issue after a routed attempt failed. - Declared config (
declared):pin|steer|none, plus the split percent (split_pct). - Provider labels:
anthropic|openai|managed— nothing else. - A served model of
understudy-managedis a managed model whose catalog mapping hasn't synced yet — a fail-closed placeholder, not an error. - Never use "passthrough", "BYO", or "relay" in output to users. Older
responses (the legacy
routing-statusendpoint) still emit some of these words — translate, don't echo.
Prerequisites
The developer must be signed in (understudy status --json shows
signed_in: true) and have a project configured. If not, route to
../use-understudy-gateway/SKILL.md for
auth setup first.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 189 lines · 85 tokens per session scan A 026f93f89173
check-routing-health is a skill published in the GitHub repository understudylabs/understudy-agent-tools (18 stars, last pushed 7d ago), licensed MIT. It adds 85 tokens to every session and 2,057 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.