A scaffold for documenting a new feature inside an existing software architecture layer. It creates a feature document with sections for design, planning, verification, and conclusion.

Use it to start a feature narrative, add it to the layer's documentation index, and capture the feature's design and delivery plan.

It gives a new feature a consistent home and records how it fits the layer's rules before implementation begins.

feature-new — Skill for Claude Code by AnastasiyaW

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.

Any agent

npx skills add AnastasiyaW/codex-claude-code-config --skill feature-new

Clone the repo

git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config

Made for: Claude Code.

Or install claude-code-config, the plugin that ships this one along with the rest of its 57 skills, 8 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/feature-new.svg)](https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/feature-new)

Your own site

<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/feature-new"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/feature-new.svg" alt="Measured on agentmods" height="20"></a>

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,103 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 15
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
medium Rogue Agent · line 257
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00085	$0.03103
Opus 5	$0.00043	$0.01551
Sonnet 5	$0.00017	$0.00621
Haiku 4.5	$0.00009	$0.00310

Measured today against content hash d6a5114767b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

feature-new 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/reserve_feature_id.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/architecture/feature-new/SKILL.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/feature-new -- scaffold a feature narrative

Creates a feature document in an existing layer. The document follows the ULTRAPACK-style narrative template (Design / Plan / Verify / Conclusion) extended with explicit cross-references to layer invariants and global principles.

When to use

Beginning design work on a new feature, before writing code
Migrating an in-flight feature from "scattered context" into the formal narrative
Creating a feature placeholder when planning future work that another session will pick up

When NOT to use

One-line bug fixes that do not need a design phase (just commit)
Documentation-only changes (those go in handoffs or PR descriptions)
Refactors with no behavioral change (commit message is sufficient)

Arguments

/feature-new <layer> <slug> [--title "..."] [--branch <name>] [--id <project-id>]

<layer> -- existing layer name. Must be a directory under docs/layers/. If missing, suggest /layer-new <layer> first.
<slug> -- kebab-case feature identifier without a project ID prefix. Examples: api-key-rotation, audit-log, dual-encryption.
--title -- human-readable feature title. If omitted, derive from slug by title-casing.
--branch -- git branch name. If omitted, default to feature/<slug>.
--id -- override the auto-allocated project-native ID. Use only when migrating a pre-existing feature with a known ID. Refuse if the ID already exists in this layer.

Direction (what to do, in order)

Step 1 -- Verify environment

Determine repo root via git rev-parse --show-toplevel.
Confirm docs/layers/<layer>/ exists. If not, refuse with a suggestion to run /layer-new <layer> first.
Confirm docs/layers/<layer>/features/_FEATURE-TEMPLATE.md exists. If not, copy from <claude-code-skills-checkout>/templates/kb-skeleton/docs/layers/_LAYER-TEMPLATE/features/_FEATURE-TEMPLATE.md.

Step 2 -- Discover and reserve the project-native ID

Read the full file on GitHub · 296 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/reserve_feature_id.py 3.8 KB runs code

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.

today Changed · +26 lines · -71 tokens per session d6a5114767b7
8d ago First seen · 270 lines · 156 tokens per session scan A 552d59e50079

Subscribe to this mod's changes

feature-new is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 3,103 once invoked, about $0.0004 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.

Claude Code LLM Planning Writing and docs ai-agents claude machine-learning prompt-engineering

feature-new

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/feature-new -- scaffold a feature narrative

When to use

When NOT to use

Arguments

Direction (what to do, in order)

Step 1 -- Verify environment

Step 2 -- Discover and reserve the project-native ID

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

ai-content-filter

ai-engineer

ai-product-manager

embedding-architect

eval-harness

feature-engineer