Tnr Dev Server

What it does

When your agent uses it

• A task needs a running local server
• A fresh test account
• Impersonated API calls — start the dev server
• Give me a test user

Example prompts

• “start the dev server”
• “give me a test user”
• “call an endpoint as a user”
• “/tnr-dev-server”

Requirements

• Docker
• A credential in AI_TEST_USER_BROKER_TOKEN
• A credential in OPENAI_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Start the server
2. 2Get the broker token
3. 3Provision test users
4. 4Call tRPC as a user
5. 5Browser login
6. 6Cleanup

What it can do on your machine

Read from SKILL.md and the folder at commit 485066e. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • make
  • curl
  • bun
  • docker

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • talented-kit-66.clerk.accounts.dev

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • AI_TEST_USER_BROKER_TOKEN
  • OPENAI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tnr Dev Server loads about 2.5k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 980 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~98

When it runs · the whole SKILL.md, loaded when a task matches

~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:12

  never source `app/.env` into your own shell or export secrets by hand to "fix" a boot error.

• NoteMentions a .env fileSKILL.md:23

  several worktrees at once. It links `app/.env`

• NoteMentions a .env fileSKILL.md:49

  with a 500 ("not configured"). `app/.env` is usually a symlink, so resolve it:

• NoteMentions a .env fileSKILL.md:53

  TEST_USER_BROKER_TOKEN=' "$(realpath app/.env)" | cut -d= -f2- | tr -d "\"'")

• NoteMentions a .env fileSKILL.md:54

  I_TEST_USER_BROKER_TOKEN in the real app/.env}"

• NoteMentions a .env fileSKILL.md:57

  applies to EVERY value read out of `app/.env`, not just this one — several

• NoteMentions a .env fileSKILL.md:171

  nt variables` at boot** — either no `app/.env` exists anywhere (`ensure-env`

• NoteMentions a .env fileSKILL.md:173

  `WARNING: no app/.env found`), or a key in the shared file is missing or invalid

• NoteMentions a .env fileSKILL.md:174

  uired). Fix the real file (`realpath app/.env`);

• NoteMentions a .env fileSKILL.md:176

  - **`app/.env` is shared** — it is a symlink to one canonical file, so editing it repoints *every*

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 980 words (~2,458 tokens).

name

tnr-dev-server

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/tnr-dev-server of studie-tech/TheNinjaRPG.

Open the folder on GitHubat commit 485066e