clickproof CLAUDE.md

clickproof CLAUDE.md is an instructions file for coding agents from sandeep-alluru/clickproof. It costs 254 tokens per session, scanned A, original, MIT.

A project instruction file for clickproof, a proposed tool that records verified facts about how graphical user interfaces behave across app versions.

In plain words
What is it for?
Use it when planning or building clickproof. The documented proposal includes Playwright-based observations, version fingerprints, a local SQLite store, and a query for previously verified interface facts.
Why use it?
It preserves the project's current decisions and next steps, helping an agent avoid returning to abandoned ideas or losing context between coding sessions.

Instructions file

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

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 clickproof CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandeep-alluru/clickproof/claude-md.svg)](https://agentmods.dev/instructions/sandeep-alluru/clickproof/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sandeep-alluru/clickproof/claude-md"><img src="https://agentmods.dev/badge/instructions/sandeep-alluru/clickproof/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 254 This file is loaded in full into every session.
When invoked 254 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 $0.00254 $0.00254
Opus 5 $0.00127 $0.00127
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00025 $0.00025

Measured 3d ago against content hash 8194971a4cbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clickproof CLAUDE.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 3d 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.

CLAUDE.md · 24 lines

What it actually says

clickproof — Session Anchor

Research spec: ../tech-research/07-Computer-and-Browser-Use/meridian-an-open-protocol-for-persistent-cross-session-g/README.md
One-liner: Continuously-verified, version-pinned GUI behavioral facts for agents — skip re-discovery
Phase: backlog
Stack: Python, playwright, sqlite3 (stdlib), sentence-transformers

Key decisions

  • Reframed from "crowdsourced OSM" (that framing died) to "freshness-verification pipeline"
  • Focus: version-pinned freshness, NOT crowdsourcing

Next step

Read the research spec (especially the dossier reframe section), then design the app-version fingerprinting scheme.

MVP definition

  • pip install clickproof works
  • Lightweight SDK that instruments Playwright agents to emit UI behavioral observations
  • App-version fingerprinting via DOM structure hash
  • SQLite-backed local knowledge store
  • Query API: clickproof.get_facts(app, min_confidence=0.8)
  • Demo: second Playwright run queries the store and skips re-discovery of known UI paths
  • README with before/after latency comparison
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. 3d ago First seen · 24 lines · 254 tokens per session scan A 8194971a4cbb

Subscribe to this mod's changes

clickproof CLAUDE.md is an instructions file published in the GitHub repository sandeep-alluru/clickproof (0 stars, last pushed 17d ago), licensed MIT. It adds 254 tokens to every session, about $0.0013 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 2026-08-31.