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 commands/sj817/claude-code-plugin-hud/setupgit clone --depth 1 https://github.com/sj817/claude-code-plugin-hudWhat 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 | $0.00013 | $0.01169 |
| Opus 5 | $0.00006 | $0.00584 |
| Sonnet 5 | $0.00003 | $0.00234 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
setup 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are configuring the claude-code-plugin-hud statusline. Goal: detect the user's
platform, pick the matching prebuilt binary bundled under this plugin's dist/,
and write a statusLine entry into their settings.json pointing at it.
The plugin's root directory is available as the environment variable
${CLAUDE_PLUGIN_ROOT}. The prebuilt binaries live at:
${CLAUDE_PLUGIN_ROOT}/dist/<rust-target-triple>/claude-hud[.exe]
Step 1 — Detect platform and architecture
Use the harness environment context (Platform:) plus a probe. Map to a Rust
target triple and binary name:
Platform (uname/env) |
Arch | Target triple | Binary |
|---|---|---|---|
macOS (darwin) |
arm64 | aarch64-apple-darwin |
claude-hud |
macOS (darwin) |
x86_64 | x86_64-apple-darwin |
claude-hud |
| Linux (glibc) | x86_64 | x86_64-unknown-linux-gnu |
claude-hud |
| Linux (glibc) | aarch64 | aarch64-unknown-linux-gnu |
claude-hud |
| Linux (musl/Alpine) | x86_64 | x86_64-unknown-linux-musl |
claude-hud |
| Linux (musl/Alpine) | aarch64 | aarch64-unknown-linux-musl |
claude-hud |
Windows (win32) |
x86_64 | x86_64-pc-windows-msvc |
claude-hud.exe |
Windows (win32) |
arm64 | aarch64-pc-windows-msvc |
claude-hud.exe |
- macOS/Linux: run
uname -smto get OS and arch (arm64/aarch64vsx86_64). - Linux glibc vs musl: prefer the
-gnubuild. Use-muslonly when glibc is absent (e.g. Alpine) — a quick check isldd --version 2>&1 | grep -qi musl. - Windows: usually
x86_64; pickaarch64-pc-windows-msvcon ARM devices (Surface Pro X, etc). Claude Code may route the command through Git Bash or PowerShell — either launches the.exedirectly.
Step 2 — Verify the binary exists
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.
- 2d ago First seen · 88 lines · 13 tokens per session scan A 1bcc738fd686
setup is a command published in the GitHub repository sj817/claude-code-plugin-hud (3 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 1,169 once invoked, about $0.0001 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.
Other commands, from other repositories
setup
Configure cc-hud statusline in Claude Code settings.
setup
Configure claude-ultimate-hud as your statusline.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.