Tianji is a self-hosted application that combines website analytics, uptime monitoring, server-status tracking, notifications, telemetry, and related tools in one service. It is intended for users who need lightweight insight into websites, servers, and deployments without running several separate monitoring applications.
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.
npx skills add msgbyte/tianji --skill tianji-workergit clone --depth 1 https://github.com/msgbyte/tianjiWrote 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/msgbyte/tianji/tianji-worker)<a href="https://agentmods.dev/skills/msgbyte/tianji/tianji-worker"><img src="https://agentmods.dev/badge/skills/msgbyte/tianji/tianji-worker/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/msgbyte/tianji/tianji-worker"><img src="https://agentmods.dev/badge/skills/msgbyte/tianji/tianji-worker.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 | $0.00038 | $0.00804 |
| Opus 5.5 | $0.00015 | $0.00322 |
| Sonnet 5.5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
tianji-worker scanned grade A with 1 finding 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 24d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
async fetch(payload, context) { How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tianji Worker
Operate Tianji Workers using the dashboard, CLI, and supported management API.
Start here
- Identify the requested operation, Tianji server, workspace, and existing Worker ID or new Worker name. Use existing configuration where available; never guess a target.
- Fetch and read the target instance's
/open/_documentbefore operating a Worker. Use its OpenAPI document to confirm exported operations, HTTP methods, paths, and parameter/body schemas. Follow Connect and inspect for discovery and unavailable-document handling; bundled examples are not the target's API contract. - Read Common operations for configuration preservation and execution rules. Operations absent from OpenAPI require the separately maintained dashboard tRPC reference; never derive an OpenAPI route from a procedure name.
- Before writing or modifying code, read Runtime reference. Tianji's sandbox differs from Node.js, browsers, and Cloudflare Workers.
- For an existing Worker, inspect its current code, active state, cron settings, and revisions before changing it. Preserve unrelated settings. Carry out the user's authorized scope; a request for sample code alone does not authorize deployment.
Choose the supported interface
| Task | Interface |
|---|---|
| Create a local project; pull compiled code | tianji worker init; tianji worker pull |
| Create or update a deployed Worker | Dashboard or OpenAPI upsert; CLI deploy has configuration side effects |
| Test draft code and payloads | Target OpenAPI if exported; otherwise dashboard Test Code / preview |
| Invoke a public Worker | HTTP /api/worker/{workspaceId}/{workerId} |
| Run a stored Worker manually; inspect logs | Target OpenAPI if exported; otherwise dashboard Executions / run action |
| Configure cron, Text/Secret variables, module bindings | Dashboard edit form; read preservation rules before API updates |
| Inspect or roll back code revisions | Dashboard Revisions or OpenAPI |
| Pause/resume; delete | OpenAPI or dashboard; deletion requires workspace admin rights |
What ships with it
2 files 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.
- 24d ago Changed · +1 lines 24588b3b5fa1
- 27d ago First seen · 52 lines · 38 tokens per session scan A 66f069c8765d
tianji-worker is a skill published in the GitHub repository msgbyte/tianji (3,109 stars, last pushed 3d ago), licensed Apache-2.0. It adds 38 tokens to every session and 804 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other skills, from other repositories
dokku-deploy
PaaS deployment with Dokku.
cloudflare-skill
Work with Cloudflare via the official cf CLI — find the right cf command, list zones, list/create/edit/delete DNS records, query the GraphQL Analytics API (zone traffic, Web Analytics/RUM), and run any other cf command (Workers, R2, KV, D1, Pages, cache). Output is parsed JSON.
gcloud-skill
Work with Google Cloud via the official gcloud CLI — check auth/config, list and switch projects, manage Compute Engine instances, deploy and inspect Cloud Run services, work with Cloud Storage, and run any other gcloud command. Output is parsed JSON.
vercel-skill
Deploy sites and apps to Vercel, inspect deployments, stream logs, and manage projects/env/domains via the Vercel CLI. Deploy a directory and get back the live deployment URL; everything else the CLI supports is available through the custom command passthrough.
aws-skill
Work with Amazon Web Services through the official boto3 SDK — check the identity behind the key, list, start and stop EC2 instances, list, upload, download and delete S3 objects, and call any other AWS API operation. Output is AWS's own JSON response.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.