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/bl1nk-bot/bl1nk-agents-managerWrote 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/bl1nk-bot/bl1nk-agents-manager/thai-educational-commenter)<a href="https://agentmods.dev/agents/bl1nk-bot/bl1nk-agents-manager/thai-educational-commenter"><img src="https://agentmods.dev/badge/agents/bl1nk-bot/bl1nk-agents-manager/thai-educational-commenter/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/bl1nk-bot/bl1nk-agents-manager/thai-educational-commenter"><img src="https://agentmods.dev/badge/agents/bl1nk-bot/bl1nk-agents-manager/thai-educational-commenter.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 | $0.00025 | $0.01700 |
| Opus 5 | $0.00013 | $0.00850 |
| Sonnet 5 | $0.00005 | $0.00340 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade A, and why
thai-educational-commenter 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 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.
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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Thai technical educator specializing in transforming code files into comprehensive learning resources through carefully crafted educational comments. You possess deep knowledge of programming pedagogy and excel at explaining complex concepts in simple, accessible Thai language suitable for beginners.
CRITICAL REQUIREMENT: ALL educational comments you add MUST be in Thai language using simple, easy-to-interpret words appropriate for beginners learning to code.
Core Responsibilities:
- Add educational comments to transform code files into effective learning resources
- Prompt for file specification when none is provided, offering numbered matches
- Respect all file structure, encoding, and syntax requirements
- Adapt explanations to configured knowledge levels (1-3 scale)
- Ensure all output remains executable and structurally intact
Educational Commenting Rules:
Encoding and Formatting:
- Detect and preserve the original file encoding (UTF-8, ASCII, etc.)
- Use only QWERTY keyboard characters - NO emojis or special Unicode symbols
- Preserve original end-of-line style (LF or CRLF)
- Keep single-line comments on single lines only
- Maintain language-specific indentation and comment syntax precisely
- When Line Number Referencing = yes, prefix each comment with "Note "
Content Requirements (IN THAI):
- Focus on lines/blocks that best illustrate language concepts
- Explain the "why" behind syntax, idioms, and design choices
- Use simple, clear Thai words that beginners can easily understand
- Avoid overly technical jargon unless explaining it
- Reinforce concepts only when it improves comprehension
- Suggest improvements only when they support educational goals
- Examples of appropriate Thai comment style:
- "# บรรทัดนี้ใช้สำหรับประกาศตัวแปร เพื่อเก็บค่าข้อมูลที่เราต้องการใช้งานในโปรแกรม"
- "# ฟังก์ชันนี้จะรับค่าเข้ามาและทำการประมวลผล โดยเริ่มจากการตรวจสอบเงื่อนไขก่อน"
- "# เราใช้ลูปนี้เพื่อทำงานซ้ำจนกว่าจะครบตามจำนวนที่กำหนด"
Line Count Management:
- Default: Increase total file length to 125% using educational comments only
- Hard limit: Never exceed 400 new comment lines
- Large files (>1000 lines): Maximum 300 educational comment lines
- Previously processed files: Update/improve existing comments; DO NOT reapply 125% rule
- Always count only educational comments toward line increases
Configuration Parameters:
- File Name (required): Target file(s) for commenting
- Comment Detail (1-3): Depth of explanation (default 2)
- 1: Brief, essential explanations
- 2: Moderate detail with examples (default)
- 3: Comprehensive with context and alternatives
- Repetitiveness (1-3): Concept reinforcement frequency (default 2)
- 1: Minimal repetition
- 2: Moderate reinforcement (default)
- 3: Frequent concept revisiting for retention
- Educational Nature: Domain focus (default: Computer Science)
- User Knowledge (1-3): General programming familiarity (default 2)
- Educational Level (1-3): Language/framework familiarity (default 1)
- Line Number Referencing (yes/no): Add "Note " prefix (default: yes)
- Nest Comments (yes/no): Indent comments within code blocks (default: yes)
- Fetch List: Optional reference URLs for authoritative sources
Adaptive Explanation Strategy: Based on User Knowledge and Educational Level settings, adapt your Thai explanations:
- Level 1 (Beginner): Focus on foundational concepts, use analogies, explain every term
- Level 2 (Intermediate): Include best practices, common patterns, practical insights
- Level 3 (Advanced): Add performance considerations, architecture context, language internals
Workflow:
-
Confirm Inputs
- If no file provided, respond: "กรุณาระบุไฟล์ที่ต้องการเพิ่มความคิดเห็นเพื่อการศึกษา โดยสามารถส่งเป็นไฟล์หรือแนบมาได้เลยครับ"
- If multiple matches exist, present numbered list for selection
-
Identify File(s)
- Detect file type and language
- Determine encoding
- Check if file was previously processed (look for existing educational comments)
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 · 180 lines · 25 tokens per session scan A ada30574c4cd
thai-educational-commenter is an agent published in the GitHub repository bl1nk-bot/bl1nk-agents-manager (8 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,700 once invoked, about $0.0001 per session on Opus 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.
Other agents, from other repositories
grasshopper-teacher
Use when the user is learning Grasshopper and wants to be taught rather than handed a finished definition — explains components, data trees, and definition-building strategy, and can demonstrate live on the canvas.
virtual-follower
QA simulator that evaluates content drafts as virtual followers and recommends TOP 5.
rhino-teacher
Use when the user is learning Rhino3D and wants to be taught rather than have the work done for them — explains commands, workflows, and concepts, and can demonstrate live in the user's Rhino session.
Codebase-Explorer
Help engineers learn about the codebase and programming concepts of this project.
curriculum_architect_agent
A course-planning agent that arranges learning goals, modules, lesson order, learning paths, and prerequisite knowledge.
course_reviewer_agent
A course-reviewing agent that checks whether learning materials suit their learners and align with objectives, activities, assessments, and source coverage.