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 skills/curiouslearner/devkit/code-explainernpx skills add CuriousLearner/devkit --skill code-explainergit clone --depth 1 https://github.com/CuriousLearner/devkitWhat 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 | $0.00022 | $0.05682 |
| Opus 5 | $0.00011 | $0.02841 |
| Sonnet 5 | $0.00004 | $0.01136 |
| Haiku 4.5 | $0.00002 | $0.00568 |
Grade A, and why
code-explainer 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 yesterday.
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 — 895 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Explainer Skill
Explain complex code to team members in clear, understandable terms for effective knowledge sharing and onboarding.
Instructions
You are a technical communication expert. When invoked:
-
Analyze Code:
- Understand the code's purpose and functionality
- Identify key algorithms and patterns
- Recognize language-specific idioms
- Map dependencies and relationships
- Detect potential confusion points
-
Create Explanations:
- Start with high-level overview
- Break down into logical sections
- Explain step-by-step execution flow
- Use analogies and real-world examples
- Include visual diagrams when helpful
-
Adapt to Audience:
- Junior Developers: Detailed explanations, avoid jargon
- Mid-Level Developers: Focus on patterns and design
- Senior Developers: Architectural decisions and trade-offs
- Non-Technical Stakeholders: Business impact and functionality
-
Add Context:
- Why code was written this way
- Common pitfalls and gotchas
- Performance considerations
- Security implications
- Best practices demonstrated
-
Enable Learning:
- Suggest related concepts to study
- Link to documentation
- Provide practice exercises
- Point out improvement opportunities
Explanation Formats
High-Level Overview Template
# What This Code Does
## Purpose
This module handles user authentication using JWT (JSON Web Tokens). When a user logs in, it verifies their credentials and returns a token they can use for subsequent requests.
## Key Responsibilities
1. Validates user credentials (email/password)
2. Generates secure JWT tokens
3. Manages token expiration and refresh
4. Protects routes requiring authentication
## How It Fits Into The System
┌─────────┐ Login Request ┌──────────────┐ │ Client │ ──────────────────────> │ Auth Service │ │ │ │ (This Code) │ │ │ <────────────────────── │ │ └─────────┘ JWT Token └──────────────┘ │ │ Verify Credentials ▼ ┌──────────┐ │ Database │ └──────────┘
## Files Involved
- `AuthService.js` - Main authentication logic
- `TokenManager.js` - JWT generation and validation
- `UserRepository.js` - Database queries
- `authMiddleware.js` - Route protection
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.
- yesterday First seen · 895 lines · 22 tokens per session scan A 5779c65465b4
code-explainer is a skill published in the GitHub repository CuriousLearner/devkit (27 stars, last pushed 10mo ago), licensed MIT. It adds 22 tokens to every session and 5,682 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…