agent-tail CLAUDE.md

agent-tail CLAUDE.md is an instructions file for coding agents from gillkyle/agent-tail. It costs 765 tokens per session, scanned A, original, MIT.

Project instructions for a monorepo, a repository containing multiple related packages, that captures browser logs and writes them to files for terminal viewing.

In plain words
What is it for?
Use it when installing dependencies, building packages, running tests, checking types, or changing the browser-log capture plugins.
Why use it?
It gives the coding agent the project structure, tools, commands, and naming rules needed to work consistently in the repository.

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/gillkyle/agent-tail/claude-md
Clone the repo
git clone --depth 1 https://github.com/gillkyle/agent-tail

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 agent-tail CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gillkyle/agent-tail/claude-md.svg)](https://agentmods.dev/instructions/gillkyle/agent-tail/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gillkyle/agent-tail/claude-md"><img src="https://agentmods.dev/badge/instructions/gillkyle/agent-tail/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 765 This file is loaded in full into every session.
When invoked 765 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 $0.00765 $0.00765
Opus 5 $0.00382 $0.00382
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00076 $0.00076

Measured 4d ago against content hash 0b4e779b80ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-tail 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 4d 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 · 83 lines

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

Project Overview

Monorepo for browser log capture plugins. Pipes browser console output to log files on disk during development, enabling terminal-based log tailing alongside backend server logs.

Packages

  • packages/core (agent-tail-core) — Shared types, log formatting, filesystem management (sessions, symlinks, pruning), client script generation, gitignore checking, CLI (agent-tail init/wrap/run)
  • packages/vite-plugin (vite-plugin-agent-tail) — Vite plugin that injects the client script and handles log ingestion via dev server middleware
  • packages/next-plugin (next-plugin-agent-tail) — Next.js plugin with config wrapper, API route handler, and script component

Tech Stack

  • TypeScript (strict mode), ESM only
  • tsdown for bundling each package
  • vitest for testing (tests/ at repo root)
  • pnpm workspaces

Commands

pnpm install              # Install all dependencies
pnpm run build            # Build all packages
pnpm run test             # Run all tests once
pnpm run test:watch       # Run tests in watch mode
pnpm run typecheck        # Type-check all packages

Code Style

  • snake_case for functions, variables, and file names
  • node: prefix for Node.js built-in imports
  • import type for type-only imports
  • 4-space indentation
  • No trailing commas in function params; trailing commas in arrays/objects

Key Concepts

  • Each dev server session creates a timestamped directory under the configured logDir
  • A latest symlink always points to the most recent session
  • Old sessions are pruned to keep only the last N (configurable via maxLogSessions)
  • Plugins warn if the log directory is not covered by .gitignore
  • Client-side script is injected into HTML and batches logs via sendBeacon
  • Multiple servers (frontend, backend, workers) can write to the same session directory
  • The CLI (agent-tail run/wrap/init) wraps arbitrary commands, piping stdout/stderr to per-service log files + combined.log

Read the full file on GitHub · 83 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. 4d ago First seen · 83 lines · 765 tokens per session scan A 0b4e779b80ef

Subscribe to this mod's changes

agent-tail CLAUDE.md is an instructions file published in the GitHub repository gillkyle/agent-tail (91 stars, last pushed 5mo ago), licensed MIT. It adds 765 tokens to every session, about $0.0038 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

jupyter-mcp-server copilot-instructions.md

Copilot instructions for datalayer/jupyter-mcp-server, covering jupyter mcp server, working effectively, environment setup, build and install (critical: network limitations) and standard installation (may fail with network issues).

datalayer/jupyter-mcp-server · 2,265 tokens

ios-simulator-skill CLAUDE.md

Instructions for conorluddy/ios-simulator-skill, covering claude.md - developer guide, project overview, project structure, architecture patterns and pattern 1: class-based script design.

conorluddy/ios-simulator-skill · 2,315 tokens

llm-context.py CLAUDE.md

Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.

cyberchitta/llm-context.py · 582 tokens

claude-scientific-writer AGENTS.md

AGENTS.md instructions for K-Dense-AI/claude-scientific-writer, covering claude agent system instructions, core mission, critical: real citations only & diverse referencing policy, critical: parallel web search policy and critical: save all research results to sources folder.

K-Dense-AI/claude-scientific-writer · 5,414 tokens

dev-challenge CLAUDE.md

Instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.

micheltlutz/dev-challenge · 543 tokens