tarn AGENTS.md

tarn AGENTS.md is an instructions file for Codex, OpenCode from NazarKalytiuk/tarn. It costs 2,678 tokens per session, scanned C, original, MIT.

Repository instructions for Tarn, a command-line tool for testing APIs. Tests are written in YAML, can send requests and check responses, and can return structured JSON results for other programs to process.

In plain words
What is it for?
Use them to create, validate, list, and run API tests, including checking status codes, response fields, captured values, headers, and environment-based URLs.
Why use it?
They give an agent the exact test format and commands needed to validate API behavior without writing separate test code for every request.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/nazarkalytiuk/tarn/agents-md
Clone the repo
git clone --depth 1 https://github.com/NazarKalytiuk/tarn

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for tarn AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nazarkalytiuk/tarn/agents-md.svg)](https://agentmods.dev/instructions/nazarkalytiuk/tarn/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nazarkalytiuk/tarn/agents-md"><img src="https://agentmods.dev/badge/instructions/nazarkalytiuk/tarn/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,678 This file is loaded in full into every session.
When invoked 2,678 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02678 $0.02678
Opus 5 $0.01339 $0.01339
Sonnet 5 $0.00536 $0.00536
Haiku 4.5 $0.00268 $0.00268

Measured 4d ago against content hash 8cb0c748626f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

tarn AGENTS.md scanned grade C 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 4d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

- Code actions: **extract env var**, **capture this field**, **scaffold assert from recorded response**.
AGENTS.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tarn — AI Agent Integration Guide

Tarn is a CLI API testing tool. Tests are YAML files (.tarn.yaml), results are structured JSON.

Quick Reference

tarn run                          # run all tests in tests/
tarn run tests/users.tarn.yaml    # run specific file
tarn run --format json            # structured JSON output (for parsing)
tarn validate                     # check syntax without running
tarn list                         # list all tests

Writing a Test

name: User API
steps:
  - name: Create user
    request:
      method: POST
      url: "{{ env.base_url }}/users"
      headers:
        Content-Type: "application/json"
      body:
        name: "Jane Doe"
        email: "[email protected]"
    capture:
      user_id: "$.id"                  # JSONPath (type-preserving)
      # session:                       # header capture with regex
      #   header: "set-cookie"
      #   regex: "session=([^;]+)"
    assert:
      status: 201                      # also: "2xx", { in: [200,201] }, { gte: 200, lt: 300 }
      body:
        "$.name": "Jane Doe"
        "$.id": { type: string, not_empty: true }

  - name: Get user
    request:
      method: GET
      url: "{{ env.base_url }}/users/{{ capture.user_id }}"
    assert:
      status: 200
      body:
        "$.name": "Jane Doe"

Assertion Operators

Operator Example Description
(literal) "$.name": "Alice" Exact match
eq { eq: "Alice" } Explicit equality
not_eq { not_eq: "Bob" } Not equal
type { type: string } Type check (string/number/boolean/array/object/null)
contains { contains: "sub" } Substring or array element
not_contains { not_contains: "x" } Inverse of contains
starts_with { starts_with: "usr_" } String prefix
ends_with { ends_with: ".com" } String suffix
matches { matches: "^[a-z]+$" } Regex match
not_empty { not_empty: true } Non-empty string/array/object
exists { exists: true } Field exists
length { length: 5 } Exact length
gt/gte/lt/lte { gt: 0 } Numeric comparison

Read the full file on GitHub · 247 lines

Changes

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.

  1. 4d ago First seen · 247 lines · 2,678 tokens per session scan C 8cb0c748626f

Subscribe to this mod's changes

tarn AGENTS.md is an instructions file published in the GitHub repository NazarKalytiuk/tarn (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,678 tokens to every session, about $0.0134 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

Math-To-Manim tests.instructions.md

Guidelines for writing and maintaining tests in Math-To-Manim.

HarleyCoops/Math-To-Manim · 3,569 tokens

antigravity-testing-kit GEMINI.md

Instructions for anhtester/antigravity-testing-kit, covering gemini ai - global automation agent rules, git pull restriction rule, browser rules (mandatory), 🖥️ viewport & mode and 🔄 thứ tự debug bắt buộc (playwright mcp).

anhtester/antigravity-testing-kit · 3,029 tokens

android-qa-kit AGENTS.md

Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.

willbytee-sudo/android-qa-kit · 2,707 tokens

devicecloud-mcp AGENTS.md

AGENTS.md instructions for RubenGlez/devicecloud-mcp, covering devicecloud-mcp, who it's for, the problem, the promise and why it's different.

RubenGlez/devicecloud-mcp · 1,002 tokens

refract AGENTS.md

AGENTS.md instructions for valternunez/refract, covering refract — agent playbooks, playbook: verify a responsive bug fix, playbook: visual-diff before merge, playbook: screenshot a page behind a login and playbook: find horizontal overflow on a pr preview.

valternunez/refract · 988 tokens

mcp-server-tester CLAUDE.md

Claude Code instructions for gleanwork/mcp-server-tester, a project described as: Playwright-based testing and eval framework for MCP servers with LLM-as-a-judge.

gleanwork/mcp-server-tester · 5 tokens