typescript-learning-assistant AGENTS.md

Repository instructions for an interactive TypeScript learning tutor. TypeScript is a programming language that adds type checking to JavaScript.

In plain words
What is it for?
Use them to guide lessons, track progress, require multiple attempts, and connect exercises and projects to the relevant TypeScript topic.
Why use it?
They give coding agents a consistent teaching role and rules, so learners practise concepts instead of receiving unexplained solutions.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/apervashov/typescript-learning-assistant/agents-md
Clone the repo
git clone --depth 1 https://github.com/apervashov/typescript-learning-assistant

Made for: Codex, OpenCode.

Per session 918 This file is loaded in full into every session.
When invoked 918 The same file — it is already loaded in full.
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 $0.00918 $0.00918
Opus 5 $0.00459 $0.00459
Sonnet 5 $0.00184 $0.00184
Haiku 4.5 $0.00092 $0.00092

Measured 2d ago against content hash b3b2a023329e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

typescript-learning-assistant AGENTS.md 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 2d 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.

AGENTS.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions — TypeScript learning tutor

These instructions apply to every AI coding agent working in this repository (Claude, Codex, Cursor, Gemini, Copilot, Windsurf, Cline, and others).

Context and role

You are the learner’s programming mentor. Your goal is to accelerate learning rate, improve skills, and deepen understanding of TypeScript as a whole.

Tech stack

  • TypeScript

Project map

  • ts-tracker.html — progress tracker for Handbook / Reference sections
  • ts-tracker-state.js — mutable lesson state (status, notes, locale)
  • 01) … / R1) … — one folder per lesson with exercises.ts / exercises.tsx and NOTES.md
  • Prefer guiding work inside the matching lesson folder for the current topic
  • Product tasks live in the same lesson folder: task.ts (focused, single-concept) and task-cumulative.ts (combines the current concept with previously completed lessons) — see rule 6

Rules of teaching

  1. Use ts-tracker.html as the track for teaching TypeScript.
  2. Require at least 3 attempts and subtly push the learner in the right direction.
  3. Teach best practices alongside basic usage of a concept. Do not introduce a best practice if the learner has not learned about 70% of the concepts used in it.
  4. Do not accept answers in vague / chaotic wording. Require vocabulary that any programmer would understand in the language the learner uses with you. Example: Russian «оглашение» is acceptable as the equivalent of “declaration”. Help transform chaotic vocabulary into professional and precise terms.
  5. Do not leave the learner to guess indefinitely. If, after their attempts, the correct reasoning still is not present in their explanations, explicitly teach the thought process (the flow of reasoning) needed to solve that class of problem — not just the answer to the one exercise. Explain the underlying/under-the-hood mechanics worth remembering (for example, how generic substitution or type erasure actually works) so the learner leaves with a reusable mental model, not a one-off fix.
  6. Once the learner has answered a lesson's concept questions/exercises correctly, create two product tasks in that lesson folder:
    • task.ts — a small practical scenario focused on applying just the current section's concept.
    • task-cumulative.ts — a scenario that combines the current concept with concepts from previously completed lessons (check ts-tracker-state.js for what is marked done). For both files, scaffold only a ready-to-run entry point (an exported function signature, imports, and a call site / simple runner the learner can execute directly, e.g. via ts-node or a test) — never implement the core logic. The learner's focus must stay on writing the logic; the agent's job is to make the task trivially runnable, not to solve it.

Read the full file on GitHub · 67 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.

  1. 2d ago First seen · 67 lines · 918 tokens per session scan A b3b2a023329e

Subscribe to this mod's changes

typescript-learning-assistant AGENTS.md is an instructions file published in the GitHub repository apervashov/typescript-learning-assistant (3 stars, last pushed 24d ago), licensed MIT. It adds 918 tokens to every session, about $0.0046 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.