leashd: Command for Claude Code

.claude/commands/healer.md

healer is a command for Claude Code from vmehera123/leashd. It costs 0 tokens per session (103 once invoked), scanned A, original, Apache-2.0.

A Playwright test helper that investigates failing browser tests and repairs their selectors, checks, or waiting logic. Playwright is a tool for testing websites in a browser.

In plain words
What is it for?
Use it to run the failing Playwright test suite, inspect traces and the current page, fix the test, and run it again.
Why use it?
It shortens the process of finding why a browser test fails and confirming that the repaired test works.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is vmehera123/leashd's own configuration. It tells Claude Code how to work on leashd 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 leashd configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vmehera123/leashd. 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/vmehera123/leashd/main/.claude/commands/healer.md
Clone the repo
git clone --depth 1 https://github.com/vmehera123/leashd

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 healer

README.md
[![agentmods](https://agentmods.dev/badge/commands/vmehera123/leashd/healer.svg)](https://agentmods.dev/commands/vmehera123/leashd/healer)
Your own site
<a href="https://agentmods.dev/commands/vmehera123/leashd/healer"><img src="https://agentmods.dev/badge/commands/vmehera123/leashd/healer.svg" alt="Measured on agentmods" 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 103 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00103
Opus 5 $0.00000 $0.00051
Sonnet 5 $0.00000 $0.00021
Haiku 4.5 $0.00000 $0.00010

Measured 6d ago against content hash 2ab412d88d84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

healer 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 6d 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/healer.md · 10 lines

What it actually says

Use the playwright test healer agent to verify that the latest tests are working and repair them otherwise.

When healing tests:

  1. Run the failing test suite with npx playwright test to identify failures
  2. For each failing test, analyze the Playwright trace file
  3. Use browser_snapshot to inspect the current UI state
  4. Compare expected vs actual state and determine root cause
  5. Fix the test code (update selectors, assertions, or waits)
  6. Re-run to confirm the fix
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. 6d ago First seen · 10 lines · 0 tokens per session scan A 2ab412d88d84

Subscribe to this mod's changes

healer is a command published in the GitHub repository vmehera123/leashd (5 stars, last pushed 11d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 103 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 2026-08-31.