clickproof AGENTS.md

Project guidance for coding agents working on clickproof, a system that stores reliable facts about how graphical interfaces behave. It describes the project, testing commands, and areas that need care.

In plain words
What is it for?
Use it when modifying clickproof to understand its purpose and run its test, lint, and type-check commands.
Why use it?
Agents working with graphical interfaces can repeat incorrect assumptions about clicks and other actions. This file provides project context and basic validation commands.

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/sandeep-alluru/clickproof/agents-md
Clone the repo
git clone --depth 1 https://github.com/sandeep-alluru/clickproof

Made for: Codex, OpenCode.

Per session 133 This file is loaded in full into every session.
When invoked 133 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 81% copy Near-identical to another mod 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 $0.00133 $0.00133
Opus 5 $0.00067 $0.00067
Sonnet 5 $0.00027 $0.00027
Haiku 4.5 $0.00013 $0.00013

Measured yesterday against content hash b9e1b8f98aa1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clickproof 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 yesterday.

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.

Origin

This is a copy

81% identical to groundcrew AGENTS.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 31 lines

What it actually says

clickproof — Agent Context

This file describes the project architecture for AI coding assistants (Claude Code, Cursor, Copilot).

What this project does

Persistent GUI behavioral facts for computer-use agents

Module map

src/clickproof/
├── # TODO: fill in module map

Key invariants

  • TODO: document invariants that must not be broken

Testing

make test       # full test suite
make lint       # ruff check + format
make typecheck  # mypy

What NOT to change without careful thought

  • TODO: list protected areas

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. yesterday First seen · 31 lines · 133 tokens per session scan A b9e1b8f98aa1

Subscribe to this mod's changes

clickproof AGENTS.md is an instructions file published in the GitHub repository sandeep-alluru/clickproof (0 stars, last pushed 15d ago), licensed MIT. It adds 133 tokens to every session, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to groundcrew AGENTS.md, differing in 6 lines, and is treated as a copy.