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.
npx agentmods add skills/ai-screams/howl/setupnpx skills add ai-screams/Howl --skill setupgit clone --depth 1 https://github.com/ai-screams/HowlWrote 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/skills/ai-screams/howl/setup)<a href="https://agentmods.dev/skills/ai-screams/howl/setup"><img src="https://agentmods.dev/badge/skills/ai-screams/howl/setup.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.00635 |
| Opus 5 | $0.00026 | $0.00318 |
| Sonnet 5 | $0.00011 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade B, and why
setup scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. Configure `~/.claude/settings.json` to use Howl as the statusline Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Verify `curl` is available How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Howl Setup
Install and configure the Howl statusline HUD for Claude Code.
What This Does
- Download the latest Howl binary from GitHub Releases
- Install it to
~/.claude/hud/howl - Configure
~/.claude/settings.jsonto use Howl as the statusline - Prompt the user to restart Claude Code
Installation
Run the install script:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/install.sh"
Verify Installation
After the script completes, verify the binary works:
echo '{}' | ~/.claude/hud/howl
The output should show a statusline with default values. If the binary is not found or fails, check:
~/.claude/hud/howlexists and is executable- Run
chmod +x ~/.claude/hud/howlif needed
Post-Install
Inform the user:
- Binary installed to
~/.claude/hud/howl - Statusline configured in
~/.claude/settings.json - Restart Claude Code to activate the statusline
Auto-Update
Once installed, the binary keeps itself current automatically:
- Claude Code auto-updates the plugin content (skills, scripts) from the marketplace.
- The plugin's
SessionStarthook (scripts/sync-binary.sh) then detects a plugin version change and re-downloads the matching binary in the background — so the binary never drifts from the plugin. It is a no-op (no network) when already in sync, and only updates an existing install (it never installs unprompted).
To receive updates, ensure marketplace auto-update is enabled for the Howl marketplace (third-party marketplaces are not auto-updated by default):
# Refresh the marketplace and update installed plugins
claude plugin marketplace update ai-screams-howl
To force a binary update immediately, just re-run this setup (/howl:setup) or
bash "${CLAUDE_PLUGIN_ROOT}/scripts/install.sh".
Troubleshooting
If the install fails:
- Check internet connectivity (needs access to github.com)
- Verify
curlis available - Try manual download from: https://github.com/ai-screams/howl/releases/latest
- Supported platforms: macOS (arm64/amd64), Linux (arm64/amd64)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 81 lines · 53 tokens per session scan B 3280a513930c
setup is a skill published in the GitHub repository ai-screams/Howl (5 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 635 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
write-view
Write, choose or repair a .view template for @tayomi/cc-views, the engine that renders a Claude Code message as a framed terminal view. Use when the user wants a report, banner, status list or table drawn instead of printed as plain text, when a view: block renders as raw text instead of drawing, or when they ask to…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
codex-test-gen
Generate unit tests for specified functions using Codex MCP.
brand-docx
Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…