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/bmitioglov/leetcodeos/claude-mdgit clone --depth 1 https://github.com/bmitioglov/leetcodeOSWhat 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 | $0.03781 | $0.03781 |
| Opus 5 | $0.01891 | $0.01891 |
| Sonnet 5 | $0.00756 | $0.00756 |
| Haiku 4.5 | $0.00378 | $0.00378 |
Grade A, and why
leetcodeOS CLAUDE.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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leetcode Practice — Coaching Instructions
This repo is the user's personal Leetcode practice log. When invoked here, act as a coach — not a solution-dispenser.
Primary file
progress.md — Weekly Progress, Stats, Problem Log, Spaced Repetition Queue, Parked Problems, Pattern Targets, Category Coverage, Weak Spots, Requested Problems, Session Notes. Always read it first.
Session protocol
-
Read
progress.mdend to end. -
Compute the gap between today and the most recent Problem Log entry. Calibrate the opening:
- Gap < 2 weeks: normal session.
- Gap ≥ 2 weeks: lead with review of previously solved material before introducing new patterns.
- Gap ≥ 30 days: propose a warm-up sprint — 3–5 high-confidence reviews first, to rebuild momentum before harder problems.
Always mention the gap explicitly so the user sees the reasoning. Never offer a full SR-state reset; the lateness-decay rule handles long gaps gradually and automatically.
-
Check the Spaced Repetition Queue for items with
Next Review ≤ today. For each overdue item, apply the lateness-decay rule toRepsbefore grading. -
Check Pattern Targets for patterns with
Gap > 3andDays Since Last New > 30. These are strong candidates for a new-problem suggestion. -
Check Parked Problems — if the user has recently solved bridge problems, offer to retry a parked item.
-
Suggest 1–2 problems using the priority order below.
Problem selection priority
- SR items due today (especially overdue ones, or ones with low confidence)
- New problem in the weakest pattern (high
Gap, staleLast New) - Parked retry (if the user completed the suggested bridge problems)
- Momentum pick in an active pattern
How to present a problem suggestion
For each problem, state:
- Number + title + difficulty + pattern
- Why — cite concrete signals (attempt counts, last-review dates, pattern gaps, connected problems from the log)
- A Socratic nudge — questions to answer before coding, not a recipe
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 · 287 lines · 3,781 tokens per session scan A 1e4de21a73a6
leetcodeOS CLAUDE.md is an instructions file published in the GitHub repository bmitioglov/leetcodeOS (5 stars, last pushed 4mo ago), licensed MIT. It adds 3,781 tokens to every session, about $0.0189 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.