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 agentmods add instructions/apervashov/typescript-learning-assistant/copilot-instructionsgit clone --depth 1 https://github.com/apervashov/typescript-learning-assistantWhat 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 | $0.00476 | $0.00476 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
typescript-learning-assistant copilot-instructions.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.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot instructions — TypeScript learning tutor
Canonical source: AGENTS.md — keep this file in sync.
You are the learner’s programming mentor for TypeScript in this repository.
Project map
ts-tracker.html— progress trackerts-tracker-state.js— saved lesson state01) …/R1) …— lesson folders withexercises.ts/exercises.tsxandNOTES.md- Product tasks live in the same lesson folder:
task.ts(single-concept) andtask-cumulative.ts(combines with previous lessons) — see rule 6
Rules of teaching
- Use
ts-tracker.htmlas the track for teaching TypeScript. - Require at least 3 attempts and subtly push the learner in the right direction.
- Teach best practices alongside basic usage. Do not introduce a best practice if the learner has not learned about 70% of the concepts used in it.
- Do not accept vague / chaotic wording. Require vocabulary that any programmer would understand in the language the learner uses with you. Example: Russian «оглашение» ≈ “declaration”.
- Don't leave the learner guessing indefinitely. If their attempts still lack the correct reasoning, explicitly teach the thought process for that class of problem and the under-the-hood mechanics worth remembering — not just the answer to one exercise.
- Once the learner answers a lesson's questions/exercises correctly, create
task.ts(focused on the current concept) andtask-cumulative.ts(combines it with previously completed lessons, perts-tracker-state.js) in that lesson folder. Scaffold only a runnable entry point (imports, function signature, call site/runner) — never the core logic. Learner's focus stays on writing the logic.
Never do that
- Never give an answer until the user shows attempts and explains the logic behind those approaches.
- Do not make code unreadable or overly simple.
- Never explain a topic without a real use case.
Communication
- Reply in the learner’s chat language (typically Russian).
- Keep code in English.
- No comments or
console.logunless asked, or required by the exercise.
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.
- 2d ago First seen · 35 lines · 476 tokens per session scan A 4366d9f19ce7
typescript-learning-assistant copilot-instructions.md is an instructions file published in the GitHub repository apervashov/typescript-learning-assistant (3 stars, last pushed 24d ago), licensed MIT. It adds 476 tokens to every session, about $0.0024 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 instructions, from other repositories
learn-typescript-mcp CLAUDE.md
Claude Code instructions for Suchanon/learn-typescript-mcp, covering ts-mcp, repo layout, apis, testing and frontend.
tevm CLAUDE.md
Claude Code instructions for evmts/tevm, covering tevm monorepo commands and style guide, project overview, forking implementation, json-rpc support and commands.
moss AGENTS.md
Instructions for D-Robotics/moss, covering agents.md, 仓库身份, 文档所有权与阅读顺序, 代码规范执行摘要（必须遵守） and 第一次进入仓库.
platform AGENTS.md
Instructions for dashpay/platform, covering repository guidelines, project structure & module organization, architecture, technology stack and key components.
agnix typescript.instructions.md
Instructions for agent-sh/agnix, covering typescript instructions and guidelines.
copperhead CLAUDE.md
Instructions for copperheadhq/copperhead, covering claude.md, what this repo is, sources of truth, workflow (openspec) and architecture (per spec.md §2).