homebrew-pandafilter: Command for Claude Code

.claude/commands/test.md

test is a command for Claude Code from AssafWoo/homebrew-pandafilter. It costs 0 tokens per session (450 once invoked), scanned A, original, MIT.

A command that runs PandaFilter's required verification checks in a fixed order. The checks cover workspace tests, handler benchmarks, fixture recall, and repository benchmarks.

In plain words
What is it for?
Running Rust tests, benchmark checks, fixture evaluation, and repository-wide performance checks before committing changes.
Why use it?
It provides one pre-commit gate instead of relying on separate manual checks. It stops at the first failure or at a measured savings regression.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is AssafWoo/homebrew-pandafilter's own configuration. It tells Claude Code how to work on homebrew-pandafilter 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 homebrew-pandafilter configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/assafpetronio/Desktop/ccr.

Reuse

Borrowing it

Nothing to install: this file belongs to AssafWoo/homebrew-pandafilter. 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/AssafWoo/homebrew-pandafilter/main/.claude/commands/test.md
Clone the repo
git clone --depth 1 https://github.com/AssafWoo/homebrew-pandafilter

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 test

README.md
[![agentmods](https://agentmods.dev/badge/commands/assafwoo/homebrew-pandafilter/test/github.svg)](https://agentmods.dev/commands/assafwoo/homebrew-pandafilter/test)
Your own site
<a href="https://agentmods.dev/commands/assafwoo/homebrew-pandafilter/test"><img src="https://agentmods.dev/badge/commands/assafwoo/homebrew-pandafilter/test/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.

agentmods 80×15 button for test

Your own site · 80×15
<a href="https://agentmods.dev/commands/assafwoo/homebrew-pandafilter/test"><img src="https://agentmods.dev/badge/commands/assafwoo/homebrew-pandafilter/test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 450 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00450
Opus 5 $0.00000 $0.00225
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 9d ago against content hash d44d3ecd7d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test 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 9d 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/commands/test.md · 54 lines

What it actually says

Run full test suite

Run all PandaFilter verification steps in order. Stop and report on first failure. This is the required pre-commit gate.

Steps

Step 1 — Workspace unit + integration tests

cargo test --workspace 2>&1

Pass: zero failures (exit code 0).

Step 2 — Handler benchmarks

cargo test -p panda handler_benchmarks -- --nocapture 2>&1

Pass: zero failures. Output should show savings > 0% for all known handlers.

Step 3 — Fixture savings check (no API key needed)

cargo run -p panda-eval -- --savings-only 2>&1

Pass: exit code 0, recall ≥ 80% across fixtures.

Step 4 — Repo benchmark (29 commands, 4 repos)

python3 ccr-eval/benchmarks/run_benchmark.py --after-only 2>&1

Pass: Weighted savings line in the output shows ≥ 40%.

How to run

Execute each step above, capturing output. After each step:

  • If exit code ≠ 0 → print the failing output and stop with "BLOCKED: Step N failed."
  • If Step 4's weighted savings drops below 40% → stop with "BLOCKED: savings regression."

After all steps pass, print a summary table:

Step 1 — cargo test --workspace          PASS
Step 2 — handler_benchmarks              PASS
Step 3 — panda-eval --savings-only       PASS
Step 4 — repo benchmark                  PASS  (weighted savings: XX.X%)

All checks passed. Safe to commit.

Notes

  • Step 4 requires the benchmark repos to exist under ccr-eval/benchmarks/repos/. If repos are missing, skip Step 4 and warn the user.
  • All steps should be run from the workspace root (/Users/assafpetronio/Desktop/ccr).
  • Do not run with --release; debug builds are the pre-commit target.
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. 9d ago First seen · 54 lines · 0 tokens per session scan A d44d3ecd7d17

Subscribe to this mod's changes

test is a command published in the GitHub repository AssafWoo/homebrew-pandafilter (100 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 450 tokens. 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.