agentmods.dev

promptsonar: Instructions file for Claude Code

CLAUDE.md

promptsonar CLAUDE.md is an instructions file for Claude Code from meghal86/promptsonar. It costs 654 tokens per session, scanned A, original, MIT.

Project instructions for PromptSonar, a tool that analyzes how AI prompts and agent instructions execute. They describe the project structure, coding rules, and conventions for Claude Code.

In plain words
What is it for?
Use them when planning, changing, reviewing, testing, or reporting work in the PromptSonar project.
Why use it?
They give coding agents the repository’s shared rules and help them work in the correct files and boundaries.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is meghal86/promptsonar's own configuration. It tells Claude Code how to work on promptsonar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything promptsonar configures →

not rated 5repo 10d ago A scan 654 tokens original MIT
View source ↗ meghal86/promptsonar promptsonar.vercel.app
Reuse

Borrowing it

Nothing to install: this file belongs to meghal86/promptsonar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/meghal86/promptsonar/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/meghal86/promptsonar

Made for: Claude Code.

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 promptsonar CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/meghal86/promptsonar/claude-md/github.svg)](https://agentmods.dev/instructions/meghal86/promptsonar/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/meghal86/promptsonar/claude-md"><img src="https://agentmods.dev/badge/instructions/meghal86/promptsonar/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for promptsonar CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/meghal86/promptsonar/claude-md"><img src="https://agentmods.dev/badge/instructions/meghal86/promptsonar/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 654 This file is loaded in full into every session.
When invoked 654 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00654 $0.00654
Opus 5 $0.00327 $0.00327
Sonnet 5 $0.00131 $0.00131
Haiku 4.5 $0.00065 $0.00065

Measured 9d ago against content hash b07b4a7e742d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

promptsonar 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 9d 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Read and follow the root AGENTS.md before planning, editing, reviewing, testing or reporting completion.

AGENTS.md is the shared source of truth for:

  • coding behavior
  • project-specific invariants
  • scope limits
  • testing expectations
  • completion reporting

When instructions conflict:

  1. follow the user's explicit current task
  2. follow the nearest applicable repository instruction
  3. follow the root AGENTS.md
  4. use the smallest safe reversible interpretation

Do not duplicate or create a separate conflicting instruction system in this file.

Apply the karpathy-guidelines skill by default for implementation, bug fixes, reviews, refactoring, test creation, architecture-sensitive changes and security-sensitive changes. Do not require lengthy planning for trivial one-line changes.

PromptSonar

Deterministic AI execution-path analysis platform. Zero LLM calls during scanning.

Paths and line numbers below reflect the real layout (the engine files live under repository/, mcp/, and contextual/, not directly in src/). Line numbers drift as code changes — treat them as hints and confirm by searching for the symbol.

Structure

  • packages/core/src/repository/analyzer.ts — artifact classifier, discovery, control state
  • packages/core/src/mcp/auditor.ts — MCP analysis, capability tokens, rule engine
  • packages/core/src/contextual/verdict.ts — contextual verdict engine, severity mapping
  • packages/core/src/repository/closure.ts — repository closure, reference expansion
  • packages/core/test/fixtures/ — test fixtures
  • packages/cli/ — CLI entry point

Key functions

  • classifyFile() in repository/analyzer.ts — assigns artifact types to files (exported entry point: analyzeRepositoryArtifacts()). There is no classifyArtifact().
  • walkRepository() in repository/analyzer.ts — discovers all files
  • controlStateForFinding() in repository/analyzer.ts (~line 2212) — derives control state
  • FS_CAPABILITY_TOKENS in mcp/auditor.ts (~line 175) — filesystem detection tokens
  • evaluateContextualVerdict() in contextual/verdict.ts — contextual verdict / severity mapping
  • analyzeRepositoryExecution() in repository/analyzer.ts — main repo scan entry point; evaluateRepositoryWithClosure() in repository/closure.ts is the discovery-first (closure) entry point

Read the full file on GitHub · 73 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. 9d ago First seen · 73 lines · 654 tokens per session scan A b07b4a7e742d

Subscribe to this mod's changes

promptsonar CLAUDE.md is an instructions file published in the GitHub repository meghal86/promptsonar (5 stars, last pushed 10d ago), licensed MIT. It adds 654 tokens to every session, about $0.0033 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.

Prompt Injectionai-securityllm-securitymcpowaspprompt-engineering
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens