cli AGENTS.md

cli AGENTS.md is an instructions file for Codex, OpenCode from prolific-oss/cli. It costs 3,108 tokens per session, scanned A, original, Apache-2.0.

Coding-agent instructions for a Go command-line tool that lets researchers manage Prolific studies, participants, and data through the Prolific API.

In plain words
What is it for?
Use them when building, testing, linting, or extending resource commands in the Prolific CLI.
Why use it?
They explain the project's architecture, command layout, tools, and testing approach so code changes follow existing conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

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/prolific-oss/cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/prolific-oss/cli

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 cli AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/prolific-oss/cli/agents-md.svg)](https://agentmods.dev/instructions/prolific-oss/cli/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/prolific-oss/cli/agents-md"><img src="https://agentmods.dev/badge/instructions/prolific-oss/cli/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,108 This file is loaded in full into every session.
When invoked 3,108 The same file — it is already loaded in full.
Security scan A 0 findings. 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 5.1 $0.03108 $0.03108
Opus 5 $0.01554 $0.01554
Sonnet 5 $0.00622 $0.00622
Haiku 4.5 $0.00311 $0.00311

Measured 2d ago against content hash 8fd01c6a79ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cli AGENTS.md 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 2d 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.

AGENTS.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working on the Prolific CLI.

Project Overview

Go CLI for the Prolific research platform — used by researchers to manage studies, participants, and data collection via the Prolific API. Module: github.com/prolific-oss/cli. Binary: prolific. Go 1.26.

Stack: Cobra (CLI framework), Bubbletea (TUI), Viper (configuration). See DEVELOPMENT.md for the full development guide.

Key commands:

make install        # Install deps, git hooks, and tools (run once after cloning)
make build          # Build binary
make test           # Run tests with coverage (always run after changes)
make lint           # Run linter (always run before committing)
make test-gen-mock  # Regenerate mocks (required after interface changes)
make all            # Full workflow: clean, install, build, test

Tests run entirely with mocks. PROLIFIC_TOKEN is not needed for tests.

Architecture

cmd/                 Cobra commands (one package per API resource)
  ├── {resource}/    Each resource gets its own package
  │   ├── {resource}.go      Parent command (groups sub-commands)
  │   ├── {action}.go        Action command implementation
  │   └── {action}_test.go   Tests
  ├── shared/        Shared utilities
  └── root.go        Main CLI initialization and command registration
client/              API interface and HTTP client
  ├── client.go      API interface and Client implementation
  ├── payloads.go    Request payload structs
  └── responses.go   Response types
model/               Domain models (one package per entity)
ui/                  Rendering layer
  ├── ui.go          Common helpers (headings, money, dates, counters)
  └── {resource}/    Per-resource renderers
mock_client/         Generated mocks (do not edit manually)
version/             Build-time version info
docs/examples/       Study templates (JSON/YAML)
scripts/             Git hooks and changelog tooling

Code Patterns

Two-Level Command Structure

Read the full file on GitHub · 310 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. 2d ago First seen · 310 lines · 3,108 tokens per session scan A 8fd01c6a79ab

Subscribe to this mod's changes

cli AGENTS.md is an instructions file published in the GitHub repository prolific-oss/cli (13 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,108 tokens to every session, about $0.0155 per session on Opus 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 2026-09-03.

Related

Other instructions, from other repositories