code-generator

A structured workflow for creating or changing software from a design document. It divides implementation into phases, records whether files are created or modified, estimates work, and previews changes before they are made.

In plain words
What is it for?
Use it to build new modules, add features, refactor existing components, and generate implementation plans with tracked file changes.
Why use it?
It makes implementation easier to review by showing the planned operations and their scope in advance. The workflow also clarifies which parts are outside its responsibility, such as compiling or changing databases.

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/dqz00116/skill-lib/code-generator
Any agent
npx skills add Dqz00116/skill-lib --skill code-generator
Clone the repo
git clone --depth 1 https://github.com/Dqz00116/skill-lib

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,805 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 $0.00022 $0.01805
Opus 5 $0.00011 $0.00903
Sonnet 5 $0.00004 $0.00361
Haiku 4.5 $0.00002 $0.00180

Measured 2d ago against content hash 22e0ad01303d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-generator 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.

code-generator/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Generator Skill

Overview

Structured workflow for implementing code from design documents with clear phase separation, cost estimation, and modification tracking.

When to Use

Use this skill when you need to:

  • Implement a new module or system from a design document
  • Add features to existing codebase
  • Refactor or replace existing components
  • Generate implementation code with clear execution plan

Core Principles

1. Phase-Based Execution

  • Break implementation into logical phases
  • Each phase has clear dependencies
  • Execute sequentially, phase by phase

2. Operation Type Declaration

  • Create: New file that doesn't exist
  • Modify: Existing file requiring changes
  • Delete: Remove existing file (rare, requires explicit confirmation)

3. Cost Transparency

  • Estimate token cost for each operation
  • Calculate total cost before execution
  • Allow user to adjust scope based on budget

4. Modification Preview

  • For modify operations, show before/after diff
  • Highlight key changes
  • No surprises for user

5. Capability Boundaries

  • Can Do: Code generation, file read/write
  • Cannot Do: Git operations, database changes, compilation, external API calls

Workflow

Step 1: Analyze Design Document

Read and understand:

  • Architecture overview
  • File list and dependencies
  • Key design decisions
  • Interface contracts

Step 2: Create Execution Plan

Use this format:

## 📋 [ProjectName] Implementation Plan

### Execution Capability Statement

| Operation | Capability |
|-----------|------------|
| Code generation | ✅ Can execute |
| Database operations | ❌ Cannot execute (user handles) |
| Git/SVN operations | ❌ Do not execute |
| Compilation | ❌ Do not execute (user triggers) |

### Phase [N]: [Phase Name]

| Order | File | Path | Operation | Content | Time | Token Cost |
|-------|------|------|-----------|---------|------|------------|
| 1 | `FileName.h` | `Path/` | Create/Modify | Brief description | X min | ~X,XXX |

**Phase Subtotal**: ~X,XXX tokens

### Modification Preview

For modify operations only:

`FileName.h`:
```cpp
// Before: [current state or "None"]
// After: [new code to be added]

Phase Dependencies

Phase 1 ──► Phase 2 ──► Phase 3

Total Cost Summary

Phase Time Token Cost
1 X min ~X,XXX
2 X min ~X,XXX
Total X hours ~XX,XXX

User Confirmation Items

  1. [Specific question 1]
  2. [Specific question 2]
  3. Start confirmation: Reply "Approve plan" to begin

Read the full file on GitHub · 289 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. 2d ago First seen · 289 lines · 22 tokens per session scan A 22e0ad01303d

Subscribe to this mod's changes

code-generator is a skill published in the GitHub repository Dqz00116/skill-lib (22 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 1,805 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

academic-paper-drafting

End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.

fabioc-aloha/Alex_Skill_Mall · 34 tokens

research-first-development

Build knowledge bases that build software — research before code, teach before execute.

fabioc-aloha/Alex_Skill_Mall · 18 tokens

agent-governance

Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.

fabioc-aloha/Alex_Skill_Mall · 39 tokens

loop-implement

The single implementation loop. It plans via wiki-plan (step 2, required) into an ordered, wiki-navigated task list, then executes those tasks in order, each loading only its named wiki pages, writing tests first, getting an independent test-quality audit, and judging against done; on failure it reflects and retries…

choiyounggi/dev-loop · 94 tokens

currency-audit

Comprehensive brain file review — external freshness, internal consistency, semantic accuracy — stamp only after full assessment.

fabioc-aloha/Alex_Skill_Mall · 24 tokens

mall-self-curation

Operate the Plugin Mall's canonical vendor, contribution, scan, score, render, and validation workflows. Use when importing or refreshing curated plugins, reviewing contributor PRs, running first-party maintenance, debugging the weekly catalog refresh, or onboarding to Mall internals.

fabioc-aloha/Alex_Skill_Mall · 56 tokens