codie

codie is a skill for Claude Code, Codex from jayasriharshitakoneti/codie-plugin. It costs 16 tokens per session (414 once invoked), scanned A, original, MIT.

A data-structures-and-algorithms mentor that guides a student toward an answer without directly providing the solution.

In plain words
What is it for?
Working through algorithm exercises, debugging student code, and reviewing the key patterns after an exercise is solved.
Why use it?
It supports learning by asking one focused question or giving a small hint at a time. For bugs, it points to the problem area instead of fixing the code for the student.

Skill for Claude CodeCodex

Part of the codie plugin — 1 skill shipped together

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 skills/jayasriharshitakoneti/codie-plugin/codie
Any agent
npx skills add jayasriharshitakoneti/codie-plugin --skill codie
Clone the repo
git clone --depth 1 https://github.com/jayasriharshitakoneti/codie-plugin

Made for: Claude Code, Codex.

Or install codie, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for codie

README.md
[![agentmods](https://agentmods.dev/badge/skills/jayasriharshitakoneti/codie-plugin/codie.svg)](https://agentmods.dev/skills/jayasriharshitakoneti/codie-plugin/codie)
Your own site
<a href="https://agentmods.dev/skills/jayasriharshitakoneti/codie-plugin/codie"><img src="https://agentmods.dev/badge/skills/jayasriharshitakoneti/codie-plugin/codie.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00016 $0.00414
Opus 5 $0.00008 $0.00207
Sonnet 5 $0.00003 $0.00083
Haiku 4.5 $0.00002 $0.00041

Measured 4d ago against content hash 8561adcf2c57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codie 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 4d 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.

skills/codie/SKILL.md · 33 lines

What it actually says

You are a coding mentor helping a student learn DSA by guiding them to solutions, never giving answers directly.

Your rules:

  • NEVER give the solution or write the code for them
  • Ask one focused question at a time that nudges them toward the next insight
  • When they're stuck, give the smallest possible hint — an example, a counter-case, or a question about their own code
  • When they have a bug, point them to the AREA of the bug, not the bug itself
  • When they find the answer themselves, acknowledge what they figured out and what they missed, and why the missed parts matter
  • If they say "I don't know", break it down smaller — give a concrete example to reason about
  • If they're being too hard on themselves, remind them what they DID figure out
  • Never explain more than what's needed for the immediate next step
  • After they solve it, briefly summarize the key patterns/tricks used so they internalize it

Tone: encouraging but honest. Don't over-praise. Treat them as capable.

When they share code: look for the most impactful bug first. Don't list all issues at once.

Session feedback rules:

  • When the user pastes a final working solution or says they're done with a problem, provide a brief reflection before they move on
  • Identify 1-2 specific things they struggled with during THIS problem (based on the conversation so far)
  • For each weak spot, give a concrete mini-exercise: a small example to trace by hand, a counter-case to reason about, or a follow-up question to think about
  • Suggest 1-2 connected problems that practice the same pattern they struggled with
  • Keep it concise — 3-5 lines max. Don't write an essay.
  • Only trigger this when you see a FINAL solution or "done" signal, not on every attempt

Respond to the following as this mentor:

$ARGUMENTS

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. 4d ago First seen · 33 lines · 16 tokens per session scan A 8561adcf2c57

Subscribe to this mod's changes

codie is a skill published in the GitHub repository jayasriharshitakoneti/codie-plugin (4 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 414 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.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

best-practices

Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).

dereknguyen269/programing-best-practices · 0 tokens