code-deduplication

code-deduplication is a skill for Claude Code, Codex from alinaqi/maggy. It costs 17 tokens per session (3,753 once invoked), scanned A, original, MIT.

A coding guide for finding existing code that already provides a needed capability before adding more code.

In plain words
What is it for?
Use it when adding functions or features, or when auditing a project for overlapping implementations.
Why use it?
It reduces repeated functionality and code bloat by checking an index and searching the codebase first. New capabilities are added to the index afterward.

Skill for Claude CodeCodex

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/alinaqi/maggy/code-deduplication
Any agent
npx skills add alinaqi/maggy --skill code-deduplication
Clone the repo
git clone --depth 1 https://github.com/alinaqi/maggy

Made for: Claude Code, Codex.

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 code-deduplication

README.md
[![agentmods](https://agentmods.dev/badge/skills/alinaqi/maggy/code-deduplication.svg)](https://agentmods.dev/skills/alinaqi/maggy/code-deduplication)
Your own site
<a href="https://agentmods.dev/skills/alinaqi/maggy/code-deduplication"><img src="https://agentmods.dev/badge/skills/alinaqi/maggy/code-deduplication.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,753 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 $0.00017 $0.03753
Opus 5 $0.00009 $0.01877
Sonnet 5 $0.00003 $0.00751
Haiku 4.5 $0.00002 $0.00375

Measured 5d ago against content hash 32f336a4016c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-deduplication 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/code-deduplication/SKILL.md · 544 lines

How it starts

The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Deduplication Skill

Purpose: Prevent semantic duplication and code bloat. Maintain a capability index so Claude always knows what exists before writing something new.


Core Philosophy

┌─────────────────────────────────────────────────────────────────┐
│  CHECK BEFORE YOU WRITE                                         │
│  ─────────────────────────────────────────────────────────────  │
│  AI doesn't copy/paste - it reimplements.                       │
│  The problem isn't duplicate code, it's duplicate PURPOSE.      │
│                                                                 │
│  Before writing ANY new function:                               │
│  1. Check CODE_INDEX.md for existing capabilities               │
│  2. Search codebase for similar functionality                   │
│  3. Extend existing code if possible                            │
│  4. Only create new if nothing suitable exists                  │
├─────────────────────────────────────────────────────────────────┤
│  AFTER WRITING: Update the index immediately.                   │
│  PERIODICALLY: Run /audit-duplicates to catch overlap.          │
└─────────────────────────────────────────────────────────────────┘

Code Index Structure

Maintain CODE_INDEX.md in project root, organized by capability not file location:

# Code Index

*Last updated: [timestamp]*
*Run `/update-code-index` to regenerate*

## Quick Reference

| Category | Count | Location |
|----------|-------|----------|
| Date/Time | 5 functions | src/utils/dates.ts |
| Validation | 8 functions | src/utils/validate.ts |
| API Clients | 12 functions | src/api/*.ts |
| Auth | 6 functions | src/auth/*.ts |

---

## Date/Time Operations

| Function | Location | Does What | Params |
|----------|----------|-----------|--------|
| `formatDate()` | utils/dates.ts:15 | Formats Date → "Jan 15, 2024" | `(date: Date, format?: string)` |
| `formatRelative()` | utils/dates.ts:32 | Formats Date → "2 days ago" | `(date: Date)` |
| `parseDate()` | utils/dates.ts:48 | Parses string → Date | `(str: string, format?: string)` |
| `isExpired()` | auth/tokens.ts:22 | Checks if timestamp past now | `(timestamp: number)` |
| `addDays()` | utils/dates.ts:61 | Adds days to date | `(date: Date, days: number)` |

---

## Validation

| Function | Location | Does What | Params |
|----------|----------|-----------|--------|
| `isEmail()` | utils/validate.ts:10 | Validates email format | `(email: string)` |
| `isPhone()` | utils/validate.ts:25 | Validates phone with country | `(phone: string, country?: string)` |
| `isURL()` | utils/validate.ts:42 | Validates URL format | `(url: string)` |
| `isUUID()` | utils/validate.ts:55 | Validates UUID v4 | `(id: string)` |
| `sanitizeHTML()` | utils/sanitize.ts:12 | Strips XSS from input | `(html: string)` |
| `sanitizeSQL()` | utils/sanitize.ts:28 | Escapes SQL special chars | `(input: string)` |

---

## String Operations

| Function | Location | Does What | Params |
|----------|----------|-----------|--------|
| `slugify()` | utils/strings.ts:8 | Converts to URL slug | `(str: string)` |
| `truncate()` | utils/strings.ts:20 | Truncates with ellipsis | `(str: string, len: number)` |
| `capitalize()` | utils/strings.ts:32 | Capitalizes first letter | `(str: string)` |
| `pluralize()` | utils/strings.ts:40 | Adds s/es correctly | `(word: string, count: number)` |

---

## API Clients

| Function | Location | Does What | Returns |
|----------|----------|-----------|---------|
| `fetchUser()` | api/users.ts:15 | GET /users/:id | `Promise<User>` |
| `fetchUsers()` | api/users.ts:28 | GET /users with pagination | `Promise<User[]>` |
| `createUser()` | api/users.ts:45 | POST /users | `Promise<User>` |
| `updateUser()` | api/users.ts:62 | PATCH /users/:id | `Promise<User>` |
| `deleteUser()` | api/users.ts:78 | DELETE /users/:id | `Promise<void>` |

---

## Error Handling

| Function/Class | Location | Does What |
|----------------|----------|-----------|
| `AppError` | utils/errors.ts:5 | Base error class with code |
| `ValidationError` | utils/errors.ts:20 | Input validation failures |
| `NotFoundError` | utils/errors.ts:32 | Resource not found |
| `handleAsync()` | utils/errors.ts:45 | Wraps async route handlers |
| `errorMiddleware()` | middleware/error.ts:10 | Express error handler |

---

## Hooks (React)

| Hook | Location | Does What |
|------|----------|-----------|
| `useAuth()` | hooks/useAuth.ts | Auth state + login/logout |
| `useUser()` | hooks/useUser.ts | Current user data |
| `useDebounce()` | hooks/useDebounce.ts | Debounces value changes |
| `useLocalStorage()` | hooks/useLocalStorage.ts | Persisted state |
| `useFetch()` | hooks/useFetch.ts | Data fetching with loading/error |

---

## Components (React)

| Component | Location | Does What |
|-----------|----------|-----------|
| `Button` | components/Button.tsx | Styled button with variants |
| `Input` | components/Input.tsx | Form input with validation |
| `Modal` | components/Modal.tsx | Dialog overlay |
| `Toast` | components/Toast.tsx | Notification popup |
| `Spinner` | components/Spinner.tsx | Loading indicator |

Read the full file on GitHub · 544 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. 5d ago First seen · 544 lines · 17 tokens per session scan A 32f336a4016c

Subscribe to this mod's changes

code-deduplication is a skill published in the GitHub repository alinaqi/maggy (705 stars, last pushed 18d ago), licensed MIT. It adds 17 tokens to every session and 3,753 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.

Related

Other skills, from other repositories

rulesync

Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.

dyoshikawa/rulesync · 64 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

gitnexus

将 GitNexus 作为受控可选代码智能能力接入,用于 brownfield MCP 查询、影响面分析、 detectchanges、多仓分析和更深代码图谱证据。输出必须回落到 /team- 主链和 artifacts。.

hashgraph-online/awesome-codex-plugins · 58 tokens

loop

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…

ZaxbyHub/opencode-swarm · 72 tokens

loongsuite-pilot-insight

基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。.

alibaba/loongsuite-pilot · 91 tokens