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.
git clone --depth 1 https://github.com/techysy/10routerWrote 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/commands/techysy/10router/status)<a href="https://agentmods.dev/commands/techysy/10router/status"><img src="https://agentmods.dev/badge/commands/techysy/10router/status/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/commands/techysy/10router/status"><img src="https://agentmods.dev/badge/commands/techysy/10router/status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.00579 |
| Opus 5.5 | $0.00033 | $0.00232 |
| Sonnet 5.5 | $0.00017 | $0.00116 |
| Haiku 4.5 | $0.00008 | $0.00058 |
Grade A, and why
status 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 29d 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.
What it actually says
Show the status of the 10Router instance the user watches, by running the plugin's status script.
Steps:
-
Determine the 10Router endpoint: default
http://127.0.0.1:20127; if the user gave an address in $ARGUMENTS (e.g. a NAS IP), pass it via--endpoint. -
Determine credentials. The dashboard endpoints this command reads (
/api/settings,/api/providers,/api/usage/dashboard) accept only a JWT session cookie or the local CLI token — a virtualsk-key does not work here. Three paths, in order of preference:- Local instance (loopback endpoint): pass nothing — the script auto-derives the CLI token from the local data dir (
machine-id+auth/cli-secret). Zero configuration. - Remote instance: pass
--password <dashboard password>; the script exchanges it for a session cookie viaPOST /api/auth/login. - Explicit token: pass
--cli-token <token>if the user already has one.
- Local instance (loopback endpoint): pass nothing — the script auto-derives the CLI token from the local data dir (
-
Run:
node "$ZCODE_PLUGIN_ROOT/scripts/status.mjs"
For a remote instance:
node "$ZCODE_PLUGIN_ROOT/scripts/status.mjs" --endpoint http://<host>:<port> --password <password>
-
Report the result. The script prints three sections:
- 渠道熔断 — providers currently in a channel-wide cooldown, with remaining time and strike count.
✅ 无熔断means all channels are serving. - 账号健康 — per provider: how many connections are enabled, and which have active per-model locks.
- 用量 — today's requests/tokens/cost, plus lifetime totals, top model, cache hit rate, and streak.
- 渠道熔断 — providers currently in a channel-wide cooldown, with remaining time and strike count.
-
If the script exits non-zero, read the
error:line: exit 1 means unreachable or partial read failure (the report still prints what it could read), exit 2 means a bad argument or missing/invalid credentials — in that case ask the user for the dashboard password. -
Use
--jsonwhen the user wants machine-readable output or you need to parse specific fields. -
If the user writes in Chinese, respond in Chinese.
Arguments (all optional): $ARGUMENTS
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.
- 29d ago First seen · 40 lines · 83 tokens per session scan A f4a733562194
status is a command published in the GitHub repository techysy/10router (74 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 579 once invoked, about $0.0003 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 2026-09-18.
Other commands, from other repositories
triage
Triage Linear issue with comprehensive analysis.
router-feedback
Submit feedback about router decision or model performance.
card
Open one self-contained OverClick card.
check
View the latest screenshot from /Pictures/Screenshots.
bmad-editorial-review-structure
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure.
bmad-prfaq
Working Backwards PRFAQ challenge that stress-tests a product concept customer-first. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.