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/minhthang1009/dotclaude/feature-devnpx skills add MinhThang1009/dotclaude --skill feature-devgit clone --depth 1 https://github.com/MinhThang1009/dotclaudeWrote 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.
[](https://agentmods.dev/skills/minhthang1009/dotclaude/feature-dev)<a href="https://agentmods.dev/skills/minhthang1009/dotclaude/feature-dev"><img src="https://agentmods.dev/badge/skills/minhthang1009/dotclaude/feature-dev.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00031 | $0.01268 |
| Opus 5 | $0.00015 | $0.00634 |
| Sonnet 5 | $0.00006 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
feature-dev 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Development — Multi-phase Orchestration
A systematic feature development process: understand → explore → ask → design → implement → review → wrap up.
Core Principles
- Ask specific questions — identify all ambiguities, edge cases, unspecified behaviors. Wait for user's answer before implementing. Ask early — after understanding the codebase, before designing the architecture.
- Understand before writing — read existing code, conventions, and patterns before creating new code.
- Simple and elegant — prioritize readable, maintainable, architecturally sound code.
- Read files from agents — when launching agents, ask them to return a list of the most important files. After agents finish → read all listed files to build deep context.
- Use TodoWrite — track progress throughout all phases.
Phase 1: Discovery
Goal: Understand the feature to build.
- Create a todo list with all phases.
- Feature request:
$ARGUMENTS - If unclear, ask user:
- What problem does it solve?
- What specifically should the feature do?
- Any constraints or requirements?
- Summarize understanding, confirm with user before continuing.
Phase 2: Codebase Exploration
Goal: Understand existing code relevant to the feature.
Skip if: user says they already know the codebase ("I know already", "skip explore") — jump directly to Phase 3.
Each agent must trace through the code comprehensively, focusing on understanding abstractions, architecture, and flow of control; each focused on a different aspect of the codebase.
Launch 2-3 code-explorer agents in parallel, each with a different focus:
- Agent 1: "Find features similar to [feature] and trace implementation"
- Agent 2: "Map architecture and abstractions for [relevant area]"
- Agent 3: "Analyze current implementation of [existing feature/area], trace through code comprehensively"
- Agent 4 (optional): "Analyze UI patterns / testing approaches / extension points related to [feature]"
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.
- 4d ago First seen · 124 lines · 31 tokens per session scan A fcc7f7060c99
feature-dev is a skill published in the GitHub repository MinhThang1009/dotclaude (20 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,268 once invoked, about $0.0002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…