AGENTS.md@docs/guides/agents/systemdB
AGENTS.md@docs/guides/agents/systemd from jingbiaomei/tokdash is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add jingbiaomei/tokdash/docs/guides/agents/systemd/AGENTS.md@git:20260712.96b0f2ePins git:20260712.96b0f2e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 13 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- jingbiaomei/tokdash
- Path
docs/guides/agents/systemd/AGENTS.md- Versions recorded
- 1
- Latest version
- git:20260712.96b0f2e, committed Jul 12, 2026
- Size
- 3,999 bytes
- Repository stars
- 92
- License
- MIT
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Agent prompt: install + background-run Tokdash Goal: help the user install Tokdash and keep it running in the background for local dashboards. ## Questions to ask first - OS: Linux (systemd) or macOS (launchd)? - Bind + security: keep `127.0.0.1` (recommended) or expose on LAN (`0.0.0.0`, only if the user explicitly wants this)? - Remote access: local-only, or do they want secure remote access via `tailscale serve`? - Port: keep default `55423` or change due to conflicts? - Install method: venv vs `pipx` vs system Python? - Linux only: do they want the optional `/health` probe timer as a restart backstop? ## Procedure (do this, in order) 1. Install Tokdash (`pip install tokdash`) and record the **absolute path** of `tokdash` (`which tokdash`). 2. Verify it works in foreground: `tokdash serve --bind 127.0.0.1 --port 55423`, then open `http://127.0.0.1:55423/`. 3. Download and configure the service template with the correct **absolute** `tokdash` path. **Linux (systemd):** ```bash mkdir -p ~/.config/systemd/user TOKDASH_PATH=$(which tokdash) cat > ~/.config/systemd/user/tokdash.service << EOF [Unit] Description=Tokdash (local token & cost dashboard) …
Read the whole file at its exact version.
How to install
mdr add jingbiaomei/tokdash/docs/guides/agents/systemd/AGENTS.md@sha256:77f0f129928ce5a2The line at the top of this page pins the label git:20260712.96b0f2e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_2c5n4pb5um4c74gt)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 12, 2026.
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:55423)
- pass: Size between 200 bytes and 200 KB (3999 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No script tag
Starting a new one? Use a template for AGENTS.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
jingbiaomei/tokdash · 92 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2c5n4pb5um4c74gt GET https://markdownregistry.com/api/v1/resolve?ref=jingbiaomei/tokdash/docs/guides/agents/systemd/AGENTS.md GET https://markdownregistry.com/api/v1/blob/77f0f129928ce5a2320c15c8d88393b9dc253c057a1130ec467cf74ef77c82ea
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.