What is LynxPrompt CLAUDE.md?

Project instructions for LynxPrompt that guide planning, releases, editor configuration, and secret handling. They explain that GitHub Actions, an automated workflow service, publishes the command-line package.

Planning complex changes, following the automated publishing process, using current Cursor rule files, and storing secrets in approved locations.

They prevent unsafe release steps, outdated editor configuration, and accidental commits of passwords or API keys.

LynxPrompt CLAUDE.md — Instructions file for Claude Code by GeiserX: Project instructions for LynxPrompt that guide planning, releases, edit

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/geiserx/lynxprompt/claude-md

Clone the repo

git clone --depth 1 https://github.com/GeiserX/LynxPrompt

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/geiserx/lynxprompt/claude-md.svg)](https://agentmods.dev/instructions/geiserx/lynxprompt/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/geiserx/lynxprompt/claude-md"><img src="https://agentmods.dev/badge/instructions/geiserx/lynxprompt/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 6,159 This file is loaded in full into every session.

When invoked 6,159 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.

Model	Per session	Once invoked
Fable 5.1	$0.06159	$0.06159
Opus 5	$0.03080	$0.03080
Sonnet 5	$0.01232	$0.01232
Haiku 4.5	$0.00616	$0.00616

Measured 6d ago against content hash f3753a815414, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

LynxPrompt 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 6d 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 · 636 lines

How it starts

The opening of the file, as written. The whole thing — 636 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - AI Agent Instructions for LynxPrompt

🧠 PLAN MODE: Use Plan Mode frequently! Before implementing complex features, multi-step tasks, or making significant changes, switch to Plan Mode to think through the approach, consider edge cases, and outline the implementation strategy. Planning prevents mistakes and saves time.

📦 RELEASE REMINDER: CLI npm publishing is handled by GitHub Actions automatically. Do NOT run npm publish locally. Do NOT create git tags manually. The workflow handles everything.

⚠️ IMPORTANT: Do NOT update this file unless the user explicitly says to. Only the user can authorize changes to AGENTS.md.

❌ DEPRECATED FORMAT: .cursorrules is deprecated. Do NOT suggest or generate .cursorrules files anywhere. Cursor now uses .cursor/rules/*.mdc (directory-based MDC format). Always use .cursor/rules/ for Cursor configurations.

🔒 SECURITY WARNING: This repository is PUBLIC at github.com/GeiserX/LynxPrompt. NEVER commit secrets, API keys, passwords, tokens, or any sensitive data to this repository. All secrets must be stored in:

GitHub Secrets (for CI/CD)

Private GitOps repositories (for docker-compose)

Local .env files (gitignored)

AGENTS.md.old (gitignored, local only)

🚀 RELEASE PROCESS (CRITICAL - READ CAREFULLY)

Understanding the Release Pipeline

There are two separate workflows that work together:

release.yml - Triggered on push to main:
- Detects changes in app vs CLI since last release
- Creates git tags (app-vX.Y.Z for web, cli-vX.Y.Z for CLI)
- Creates GitHub Releases with changelogs
- Tag-only — does NOT push the version bump back to main. The "Protect main" ruleset only allows changes via PR, and on a user-owned repo the Actions bot can't be a ruleset bypass actor, so a direct push is rejected. The next version is derived from max(package.json, latest matching tag), so it stays monotonic even though package.json on main lags the tags. Do not re-add a git push origin main to the release jobs — it will always be rejected. publish-cli.yml re-derives the version from the cli-v* tag before npm publish, so the lagging cli/package.json doesn't affect published artifacts.

Read the full file on GitHub · 636 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.

6d ago First seen · 636 lines · 6,159 tokens per session scan A f3753a815414

Subscribe to this mod's changes

LynxPrompt CLAUDE.md is an instructions file published in the GitHub repository GeiserX/LynxPrompt (45 stars, last pushed 3d ago), licensed Apache-2.0. It adds 6,159 tokens to every session, about $0.0308 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 2026-08-30.

Git and workflow Releases agents-md ai-ide claude-code cursor lynxprompt vibe-coding

AI-Powered-Coding-Tools CLAUDE.md

Claude Code instructions for dereknguyen269/AI-Powered-Coding-Tools, covering claude.md, what this repo is, maintenance scripts, validate links in a markdown file and fix markdown formatting issues.

dereknguyen269/AI-Powered-Coding-Tools · 338 tokens

mda CLAUDE.md

Instructions for sno-ai/mda, covering claude.md — sno-ai/mda, release process for @markdown-ai/cli, to cut a release (any 1.1.x, 1.2.0, 2.0.0 — same flow), release notes — non-negotiable and what's new.

sno-ai/mda · 1,248 tokens

nezha CLAUDE.md

Claude Code instructions for hanshuaikang/nezha, a project described as: Code Editor for the AI Agents Era. Run multiple Claude Code and Codex agents across projects on your machine.

hanshuaikang/nezha · 4 tokens

trellis AGENTS.md

Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.

craigcossairt/trellis · 3,686 tokens

ai-agent-skills CLAUDE.md

Instructions for wednesday-solutions/ai-agent-skills, covering project guidelines, wednesday agent skills, available skills, how to use skills and important.

wednesday-solutions/ai-agent-skills · 1,285 tokens

trellis CLAUDE.md

Instructions for craigcossairt/trellis, a project described as: The structure a project grows on: a free starter template for AI-assisted development. One AGENTS.md every tool reads (Claude Code, Cursor, Grok Build, Codex, Gemini CLI, Copilot), TDD + bug-fix methodology, secret guardrails, optional local knowledge…

craigcossairt/trellis · 134 tokens