What is halal-doctor?

A read-only diagnostic command for the Halal Terminal plugin, which provides Shariah-compliant investing tools. It checks the plugin, stored credentials, API access, quota, connections, skills, and recent errors.

Use it to inspect the plugin’s health and configuration without changing anything.

It helps identify whether a problem comes from missing credentials, an invalid key, usage limits, connectivity, or the plugin setup.

halal-doctor — Command for Claude Code by goww7

Install

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.

Clone the repo

git clone --depth 1 https://github.com/goww7/halalterminal-claude-skills

Made for: Claude Code.

Or install halalterminal-claude-skills, the plugin that ships this one along with the rest of its 9 skills, 2 commands, 1 agent, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/goww7/halalterminal-claude-skills/halal-doctor/github.svg)](https://agentmods.dev/commands/goww7/halalterminal-claude-skills/halal-doctor)

Your own site

<a href="https://agentmods.dev/commands/goww7/halalterminal-claude-skills/halal-doctor"><img src="https://agentmods.dev/badge/commands/goww7/halalterminal-claude-skills/halal-doctor/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/goww7/halalterminal-claude-skills/halal-doctor"><img src="https://agentmods.dev/badge/commands/goww7/halalterminal-claude-skills/halal-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 961 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 3 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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00961
Opus 5	$0.00020	$0.00481
Sonnet 5	$0.00008	$0.00192
Haiku 4.5	$0.00004	$0.00096

Measured 11d ago against content hash d9d9e6d22d89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

halal-doctor scanned grade C with 3 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 11d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

Run the checks below in order. Report each as ✓ / ⚠ / ✗ with a one-line explanation. Keep output compact; do not lecture.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **pluginConfigs**: `~/.claude/settings.json` → `pluginConfigs["halalterminal-claude-skills@halalterminal-claude-skills"].mcpServers.halalterminal.HALALTERMINAL_API_KEY`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS -o /dev/null -w '%{http_code}' \

commands/halal-doctor.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/halal-doctor

Run the checks below in order. Report each as ✓ / ⚠ / ✗ with a one-line explanation. Keep output compact; do not lecture.

1. Plugin version

Read .claude-plugin/plugin.json from this plugin's install path. Report name and version.

2. Credentials storage

Check both locations:

Credentials file: ~/.claude/halalterminal/credentials — look for a line HALALTERMINAL_API_KEY=ht_... (length ≥ 20).
pluginConfigs: ~/.claude/settings.json → pluginConfigs["halalterminal-claude-skills@halalterminal-claude-skills"].mcpServers.halalterminal.HALALTERMINAL_API_KEY.

Report:

✓ "Both locations have matching key (last 4: XYZ9)."
⚠ "Only one of the two storage locations has the key; run /halal-setup to sync."
⚠ "The two locations have DIFFERENT keys. Run /halal-setup to reconcile."
✗ "No API key configured. Run /halal-setup." — stop here; skip remaining checks.

3. API key valid against the live API

Using the key from step 2, run:

curl -sS -o /dev/null -w '%{http_code}' \
  -H 'X-API-Key: <THE_KEY>' \
  https://api.halalterminal.com/api/education/methodologies

200 → ✓ "Key accepted."
401 / 403 → ✗ "Key rejected. Run /halal-setup to replace it."
429 → ⚠ "Key is over quota. See https://halalterminal.com/dashboard."
Other / network error → ⚠ "API unreachable right now — check status."

4. MCP bridge status

Run claude mcp list. Report one of:

✓ "Plugin MCP halalterminal-claude-skills:halalterminal is connected."
⚠ "Plugin MCP failed to connect, but a separate halalterminal MCP is registered elsewhere and is serving queries. To use the plugin's bridge exclusively, remove the other registration; otherwise this is harmless."
✗ "No halalterminal MCP is registered anywhere. Restart Claude Code after setup, or add one manually."

List every line matching halalterminal so the user can see the full picture.

5. Plan + token costs

Try curl https://api.halalterminal.com/api/keys/token-costs with the key. If 200, render the returned cost table. Otherwise fall back to this hardcoded table:

Read the full file on GitHub · 91 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.

11d ago First seen · 91 lines · 41 tokens per session scan C d9d9e6d22d89

Subscribe to this mod's changes

halal-doctor is a command published in the GitHub repository goww7/halalterminal-claude-skills (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 41 tokens to every session and 961 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 3 findings (strips warnings and disclaimers, 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.

Finance and fintech ai-agents claude-skills fintech-api halal halal-finance islamic-finance

halal-doctor

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Strips warnings and disclaimersmediumAnti-refusal

Reads agent configuration directoriesmediumAgent snooping

Makes network callslowCapability

How it starts

/halal-doctor

1. Plugin version

2. Credentials storage

3. API key valid against the live API

4. MCP bridge status

5. Plan + token costs

What this file has done since we first saw it

Other commands, from other repositories

burn-rate

unit-economics

competitive

secular-trends

sector-overview

reverse-dcf