add-feature

A workflow for adding functionality that does not yet exist in a codebase. It researches the existing structure, designs the change and guides its implementation and review.

In plain words
What is it for?
Use it when creating a new feature, module, class or API endpoint, including the surrounding architecture research and final consistency check.
Why use it?
It helps new code fit the project’s existing patterns instead of becoming an isolated addition. For larger changes, it can also define tests before implementation.

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/hellotern/sextant/add-feature
Any agent
npx skills add hellotern/Sextant --skill add-feature
Clone the repo
git clone --depth 1 https://github.com/hellotern/Sextant

Made for: Claude Code, Codex.

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,573 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 $0.00110 $0.02573
Opus 5 $0.00055 $0.01287
Sonnet 5 $0.00022 $0.00515
Haiku 4.5 $0.00011 $0.00257

Measured 2d ago against content hash e556989dc11e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-feature 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.

skills/add-feature/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

!../principles/SKILL_BODY.md

!../tool-gitnexus/SKILL_BODY.md


New Feature / Module Workflow

Core Principle

When adding new features, integrate into the existing architecture like a native, not an outsider who starts from scratch. New code should be fully consistent with existing code in style, structure, and interaction patterns.


Complete Execution Workflow

Progress tracking: At the start of each step, output an updated progress block. For Lightweight tasks show only Steps 3–4; for Medium/Large tasks show all steps.

Add Feature Progress
✓ Step 1: Architecture Research     — <one-line finding>
→ Step 2: Solution Design + Confirm — in progress
○ Step 2.5: TDD Contract Tests      — (Large/Medium only)
○ Step 3: Implement
○ Step 4: Architecture Audit

Replace with for the current step, and once complete.


Step 1: Understand the Existing Architecture

Before starting, you must be able to answer the following questions:

Architecture awareness:

  • What architectural pattern does the project use? (MVC / MVVM / Clean Architecture / Component-based / Microservices…)
  • How are similar existing features implemented? (Find the best reference)
  • What is the logic behind the project's directory structure? (By layer, by feature, by domain?)

Positioning analysis:

  • Which layer does the new feature belong to? Where is its entry point?
  • Which existing modules does the new feature need to depend on?
  • Are there already extendable abstraction points (e.g., existing strategy interfaces, factory registries, event buses), or do new ones need to be created?

Reference module:

  • Find the most similar existing module to the new feature as an implementation reference
  • Observe its file structure, naming conventions, dependency injection approach, error handling patterns, and test organization
  • The new module should follow the same patterns as closely as possible

🔗 When GitNexus is available, use query / context MCP tools for architecture exploration.

Read the full file on GitHub · 244 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 · 244 lines · 110 tokens per session scan A e556989dc11e

Subscribe to this mod's changes

add-feature is a skill published in the GitHub repository hellotern/Sextant (15 stars, last pushed 4mo ago), licensed MIT. It adds 110 tokens to every session and 2,573 once invoked, about $0.0006 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.