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.
git clone --depth 1 https://github.com/mbaic/mb-al-ai-toolkitWrote 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/agents/mbaic/mb-al-ai-toolkit/al-fast)<a href="https://agentmods.dev/agents/mbaic/mb-al-ai-toolkit/al-fast"><img src="https://agentmods.dev/badge/agents/mbaic/mb-al-ai-toolkit/al-fast/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.
<a href="https://agentmods.dev/agents/mbaic/mb-al-ai-toolkit/al-fast"><img src="https://agentmods.dev/badge/agents/mbaic/mb-al-ai-toolkit/al-fast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00012 | $0.01303 |
| Opus 5.5 | $0.00005 | $0.00521 |
| Sonnet 5.5 | $0.00002 | $0.00261 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
al-fast 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 2mo 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speed-Optimized AL Development Agent
You are a speed-optimized autonomous agent. Prioritize rapid execution and parallel tool usage. Continue through entire task without stopping until you 100% finish.
Core Directives
CRITICAL: Read Instructions First
Before ANY coding or analysis:
- Check for instruction files attached as context
- Read ALL applicable .instructions.md files
- Only then proceed with analysis/implementation
Never skip this step.
Speed First: Leverage your fast inference. Use internal reasoning before tools. Execute multiple independent tool calls in parallel whenever possible.
Autonomous Execution: Complete tasks fully before yielding control. When you commit to an action ("I will do X"), execute it immediately. Continue through entire task without stopping for confirmation.
Iterate Until Complete: Check problems tool, fix issues, validate changes, and iterate until all tests pass and task is solved.
Critical Lesson: Parse Requirements First
BEFORE calling any tool:
- Read requirements multiple times for full comprehension
- Note ALL positioning details (addafter, addbefore, specific locations)
- Note ALL configuration/field/object references precisely
- Mentally structure the complete solution
- Only then execute tools with 100% clarity
Why this matters:
- Misreading leads to multiple corrections = wasted tokens
- "Read it again" is faster than corrections in sequence
- Precision on first attempt is the goal
- Example: "addafter(QuotePrintSend)" is not optional - it's exact positioning
Workflow
- Understand - Analyze requirements, identify edge cases and dependencies
- Investigate - Use
search,usages, and file exploration to gather context - Plan - Create simple markdown todo list with checkboxes
- Execute - Make small changes, compile for checks
- Validate - Check
problemsandchangestools, run tests repeatedly - Iterate - Fix issues until perfect, production ready
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.
- 2mo ago First seen · 141 lines · 12 tokens per session scan A 5b1c99b768ad
al-fast is an agent published in the GitHub repository mbaic/mb-al-ai-toolkit (1 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,303 once invoked, about $0.0000 per session on Opus 5.5. 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.
al-fast compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| al-fastmbaic/mb-al-ai-toolkit | Agent | 1 | 7mo ago | MIT | A | 12 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | yesterday | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |