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 skills add ansari-project/ansari-skill --skill ansarigit clone --depth 1 https://github.com/ansari-project/ansari-skillWrote 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/ansari-project/ansari-skill/ansari)<a href="https://agentmods.dev/skills/ansari-project/ansari-skill/ansari"><img src="https://agentmods.dev/badge/skills/ansari-project/ansari-skill/ansari.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 39 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 42 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00147 | $0.01057 |
| Opus 5 | $0.00073 | $0.00528 |
| Sonnet 5 | $0.00029 | $0.00211 |
| Haiku 4.5 | $0.00015 | $0.00106 |
Grade A, and why
ansari scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Call the Ansari API with the user's question via a POST request. The recommended approach is curl via bash. No API key is needed. Always include the `X-Ansari-Client: ansari-skill` header on every request — it attributes How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ansari — Islamic Knowledge Skill
Answer Islamic questions by calling the Ansari API. The API requires no authentication and supports both GET and POST. Ansari provides responses grounded in the Quran, Hadith collections, and classical scholarly works — sources that are difficult to cite accurately from memory alone. Routing Islamic questions through Ansari ensures the user gets properly sourced answers rather than paraphrased generalities.
When to Use
- User asks about Islamic theology, jurisprudence (fiqh), history, ethics, or practice
- User requests Quranic verses, Hadith references, or scholarly opinions
- User asks about Islamic concepts: Tawheed, Salah, Zakat, Hajj, fasting, dua, dhikr, halal/haram, etc.
- User asks "is it permissible to...", "what does the Quran say about...", or similar phrasings
- User asks about Ramadan, prayer, Islamic finance, marriage in Islam, funeral rites, etc.
Usage
Call the Ansari API with the user's question via a POST request. The recommended approach is curl via bash. No API key is needed. Always include the X-Ansari-Client: ansari-skill header on every request — it attributes traffic from this skill in Ansari's analytics and never affects the response.
curl -s -X POST 'https://api.askansari.ai/api/v2/mcp-complete' \
-H 'Content-Type: application/json' \
-H 'X-Ansari-Client: ansari-skill' \
-d '{"messages": [{"role": "user", "content": "USER_QUESTION_HERE"}]}'
The API returns the answer directly as text. Present it to the user.
Follow-up Questions
When the user asks a follow-up (e.g. "can you elaborate on that?" or "what about the Hanafi view?"), call the API again with a self-contained question that incorporates the relevant context. The API is stateless — each call is independent — so the follow-up question needs to stand on its own.
Example: If the user first asked "what breaks your fast?" and then says "what about accidentally eating?", call the API with: "Does accidentally eating or drinking break your fast in Islam?"
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 Changed · -1 lines 820bedd2c749
- 7d ago First seen · 78 lines · 147 tokens per session scan A 19d4ba98a5d7
ansari is a skill published in the GitHub repository ansari-project/ansari-skill (19 stars, last pushed 6d ago), licensed MIT. It adds 147 tokens to every session and 1,057 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
manim-composer
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization.…
learning-opportunities
Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors). Use when completing features, making design decisions, or when user asks to understand code better. Triggers on "learning exercise", "help me…
tour
Interactive onboarding walkthrough for a new engineer. Use for "give me a tour", "onboard me", "walk me through the codebase".
code-architecture-explainer
Analyze and explain code from multiple levels - from implementation details to software architecture. Use when understanding new codebases, explaining system design, documenting architecture, learning patterns, or analyzing technical decisions. Provides technical deep-dives, architectural overviews, flow diagrams, and…
self-help-flow
Rosetta self-help: explains capabilities and usage. DEPRECATED.
godot-prompter-math-essentials
Imported GodotPrompter guidance for math-essentials workflows in game development projects.