Borrowing it
Nothing to install: this file belongs to rayapatiranjithai/prompt-analyzer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rayapatiranjithai/prompt-analyzer/main/CLAUDE.mdgit clone --depth 1 https://github.com/rayapatiranjithai/prompt-analyzerWrote 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.
[](https://agentmods.dev/instructions/rayapatiranjithai/prompt-analyzer/claude-md)<a href="https://agentmods.dev/instructions/rayapatiranjithai/prompt-analyzer/claude-md"><img src="https://agentmods.dev/badge/instructions/rayapatiranjithai/prompt-analyzer/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.
<a href="https://agentmods.dev/instructions/rayapatiranjithai/prompt-analyzer/claude-md"><img src="https://agentmods.dev/badge/instructions/rayapatiranjithai/prompt-analyzer/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01249 | $0.01249 |
| Opus 5 | $0.00624 | $0.00624 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
prompt-analyzer 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
prompt-analyzer is a Claude Code plugin (no compiled code, no test runner). It coaches the
user on how they write prompts, scores each prompt against Anthropic's documented
prompt-engineering standards, and persists per-session statistics. The "logic" lives in Markdown
skill instructions that Claude executes — not in a program. Editing this repo means editing
prompts/config, then validating with the Claude CLI.
Commands
claude plugin validate . # validate plugin.json + skills before sharing (run after any edit)
claude --plugin-dir . # run Claude Code with this plugin mounted (local dev)
Inside a Claude session:
/reload-plugins— pick up file edits without restarting./prompt-analyzer:analyze-prompt— live per-prompt coaching + Analysis Window (theanalyze-promptskill)./prompt-analyzer:prompt-report— read-only end-of-session scorecard (theprompt-reportskill).
There is no build/lint/test step. "Testing" a change = validate, /reload-plugins, then submit a
prompt and confirm the coaching/stats behave.
Architecture — the three moving parts
The whole plugin is a loop between a hook, two skills, and a per-session JSON file:
hooks/hooks.json— auto-invocation is disabled by default ("hooks": {}); coaching runs only when the user explicitly invokes/prompt-analyzer:analyze-prompt. The originalUserPromptSubmithook is preserved in the_disabled_UserPromptSubmitblock: it fires on every prompt and injects a<system-reminder>telling Claude to run the skill (a leading*exempts a prompt). To turn auto-coaching back on, move that block back underhooksand setauto_observe: trueinconfig.json. Note the hook does not readauto_observe— the flag is documentation-only, so the hook's presence/absence is the real switch.
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.
- 9d ago First seen · 83 lines · 1,249 tokens per session scan A fa7d3802cb34
prompt-analyzer CLAUDE.md is an instructions file published in the GitHub repository rayapatiranjithai/prompt-analyzer (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,249 tokens to every session, about $0.0062 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.
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.
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.
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).
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).
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.
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.