What is agent-tail CLAUDE.md?

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

Use it when installing dependencies, building packages, running tests, checking types, or changing the browser-log capture plugins.

It gives the coding agent the project structure, tools, commands, and naming rules needed to work consistently in the repository.

How gillkyle/agent-tail configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gillkyle/agent-tail. 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/gillkyle/agent-tail/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gillkyle/agent-tail

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/gillkyle/agent-tail/claude-md/github.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/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" 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. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00765	$0.00765
Opus 5.5	$0.00306	$0.00306
Sonnet 5.5	$0.00153	$0.00153
Haiku 4.5	$0.00076	$0.00076

Measured 2mo ago against content hash 0b4e779b80ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

2mo 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 (93 stars, last pushed 8mo ago), licensed MIT. It adds 765 tokens to every session, about $0.0031 per session on Opus 5.5. 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.

Debugging ai console development dx logs tools

agent-tail CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-tail CLAUDE.mdgillkyle/agent-tail	Instructions file	93	8mo ago	MIT	A	765	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-tail: Instructions file for Claude Code