feature-config

feature-config is a command for Claude Code from axiomantic/spellbook. It costs 17 tokens per session (10,748 once invoked), scanned A, original, MIT.

A setup command that gathers project preferences, detects whether work is being resumed, and records the chosen process for the current run.

In plain words
What is it for?
Use it to configure development work, resume interrupted runs, and choose how much process or review the run should use.
Why use it?
It prevents work from starting with missing decisions or repeated questions. It also helps continue an earlier session from its existing files and progress.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Use it to configure development work, resume interrupted runs, and choose how much process or review the run should use.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/feature-config
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.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Made for: Claude Code.

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 feature-config

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-config/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/feature-config)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/feature-config"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-config/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for feature-config

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/feature-config"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,748 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.
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 5.1 $0.00017 $0.10748
Opus 5 $0.00009 $0.05374
Sonnet 5 $0.00003 $0.02150
Haiku 4.5 $0.00002 $0.01075

Measured 5d ago against content hash 7e825f119e11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

feature-config 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.

commands/feature-config.md · 864 lines

How it starts

The opening of the file, as written. The whole thing — 864 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Configuration (Phase 0)

Invariant Principles

  1. Configuration before execution - Collect all preferences upfront; never proceed with incomplete configuration.
  2. Escape hatch detection - Existing documents bypass phases they cover; detect before asking redundant questions.
  3. Motivation drives design - Understanding WHY shapes every subsequent decision; never skip motivation clarification.
  4. Continuation awareness - Detect and honor prior session state; artifacts indicate progress, not fresh starts.
  5. Ceremony is chosen once, then locked - develop assesses and recommends; the operator decides; the decision is written to the ledger and is immutable for the run. Escalation stays legal; de-escalation never becomes legal.

0.5 Continuation Detection

Continuation Signals (any of):

  1. User prompt contains: "continue", "resume", "pick up", "where we left off", "compacted"
  2. MCP <system-reminder> contains **Skill Phase:** with develop phase
  3. MCP <system-reminder> contains **Active Skill:** develop
  4. Artifacts exist in expected locations for current project

If NO continuation signals: Proceed to 0.1.

If continuation signals detected:

Step 1: Parse Recovery Context

Extract from <system-reminder> (if present):

  • active_skill, skill_phase (e.g., "Phase 2: Design"), todos, exact_position

Read the full file on GitHub · 864 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 · 864 lines · 17 tokens per session scan A 7e825f119e11

Subscribe to this mod's changes

feature-config is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 10,748 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 2026-09-03.