Howl: Instructions file for Claude Code

CLAUDE.md

Howl CLAUDE.md is an instructions file for Claude Code from ai-screams/Howl. It costs 1,548 tokens per session, scanned A, original, MIT.

Project instructions for Howl, a Go program that reads JSON status data and prints an ANSI-colored status display with metrics such as context use, cost per minute, and tokens per second.

In plain words
What is it for?
Working on Howl's data pipeline, running focused or full tests, building and installing the binary, and applying project quality checks.
Why use it?
They tell an agent how the program is structured and which commands to use for building, testing, formatting, and checking it.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

This is ai-screams/Howl's own configuration. It tells Claude Code how to work on Howl 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 Howl configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ai-screams/Howl. 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/ai-screams/Howl/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ai-screams/Howl

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 Howl CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ai-screams/howl/claude-md.svg)](https://agentmods.dev/instructions/ai-screams/howl/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ai-screams/howl/claude-md"><img src="https://agentmods.dev/badge/instructions/ai-screams/howl/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,548 This file is loaded in full into every session.
When invoked 1,548 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 $0.01548 $0.01548
Opus 5 $0.00774 $0.00774
Sonnet 5 $0.00310 $0.00310
Haiku 4.5 $0.00155 $0.00155

Measured 7d ago against content hash 0fb1f44970bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Howl 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 7d 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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 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.

Project

Howl — a Go statusline HUD for Claude Code. Reads JSON from stdin (piped every ~300ms), computes 5 derived metrics (context%, cache efficiency, API wait ratio, cost/min, tokens/sec) with 12 feature toggles, and outputs ANSI-formatted lines. Zero external dependencies (stdlib only), CGO_ENABLED=0, ~10ms cold start.

Module: github.com/ai-screams/howl

Commands

make build     # CGO_ENABLED=0 go build → build/howl
make install   # build + copy to ~/.claude/hud/howl
make unit-test # go test ./... -v -cover -coverprofile=coverage.out
make test      # smoke test: pipes sample JSON into built binary
make lint      # golangci-lint run
make fmt       # go fmt ./...
make fmt-docs  # prettier on *.md *.yaml *.yml
make check     # fmt + fmt-docs + lint + unit-test
make setup     # configure .githooks + install prettier

Run a single test:

go test ./internal -run TestComputeMetrics -v
go test ./cmd/howl -run TestVersionFlag -v

Architecture

Data Pipeline (main.go)

stdin JSON → json.Decode(StdinData) → LoadConfig → ComputeMetrics → GetGitInfo → GetUsage → ParseTranscript → GetAccountInfo → Render → stdout (ANSI lines, spaces → NBSP)

Every function after ComputeMetrics is optional — returns nil on failure, and Render gracefully omits that section. This is the core design principle: graceful degradation everywhere.

internal/ Package — Single Flat Package

All business logic lives in internal/ with no sub-packages. The dependency graph between files:

  • types.goStdinData struct matching Claude Code's JSON schema, ModelTier classification
  • metrics.goMetrics struct + ComputeMetrics(): context%, cache efficiency, API wait ratio, cost/min, tokens/sec
  • constants.go — Default threshold values (danger 85%, warning 70%, moderate 50%, session cost $5/$1, cache 80/50%, API wait 60/35%, speed 60/30 tok/s, cost velocity $0.50/$0.10/min, quota 10/25/50/75%). All configurable via config.go Thresholds
  • config.goConfig + FeatureToggles + Thresholds (17 configurable color/behavior values) + 4 presets (full/minimal/developer/cost-focused). LoadConfig() reads ~/.claude/hud/config.json with 4KB size guard. Features merge via mergeFeatures(base, override) — override can only enable, not disable. Thresholds merge via mergeThresholds(base, override) — only positive values override, validated via 3-step clamping
  • render.goRender() dispatches to renderNormalMode (2-4 lines) or renderDangerMode (2 dense lines) at configurable context threshold (default 85%). Line 2 supports priority ordering (max 5 metrics)
  • git.goGetGitInfo(): branch + dirty via subprocess with 1s timeout
  • usage.goGetUsage(): OAuth quota from api.anthropic.com/api/oauth/usage, 60s session-scoped cache in /tmp/howl-{sessionID}/. Token from macOS Keychain via /usr/bin/security
  • transcript.goParseTranscript(): tail-reads last 64KB/100 lines of JSONL, extracts top-5 tools + running agents
  • account.goGetAccountInfo(): reads ~/.claude.json for email display

Read the full file on GitHub · 97 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. 7d ago First seen · 97 lines · 1,548 tokens per session scan A 0fb1f44970bd

Subscribe to this mod's changes

Howl CLAUDE.md is an instructions file published in the GitHub repository ai-screams/Howl (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,548 tokens to every session, about $0.0077 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.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

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