feature-implement

feature-implement is a command for Claude Code from axiomantic/spellbook. It costs 28 tokens per session (3,012 once invoked), scanned A, original, MIT.

A command for turning an approved feature design into a detailed implementation plan. It checks that the earlier design and understanding work are complete before planning the coding tasks.

In plain words
What is it for?
Use it to review a design, break a feature into implementation tasks, and approve the plan before coding begins.
Why use it?
It reduces the risk of starting implementation with unclear requirements or missing design decisions. The plan gives the later execution phase a checked sequence of work.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it to review a design, break a feature into implementation tasks, and approve the plan before coding begins.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/feature-implement"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,012 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 $0.00028 $0.03012
Opus 5 $0.00014 $0.01506
Sonnet 5 $0.00006 $0.00602
Haiku 4.5 $0.00003 $0.00301

Measured 5d ago against content hash 8b6ec6409675, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

feature-implement 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-implement.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/feature-implement

Phase 3 of the develop workflow. Run after /feature-design completes (Phase 2 approved). Phase 4 (implementation execution) continues in /feature-implement-execute.

Before ANY Phase 3-4 work begins, run this verification:

# ══════════════════════════════════════════════════════════════
# PREREQUISITE CHECK: feature-implement (Phase 3-4)
# ══════════════════════════════════════════════════════════════

PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
PROJECT_ENCODED=$(echo "$PROJECT_ROOT" | sed 's|^/||' | tr '/' '-')

echo "=== Phase 3-4 Prerequisites ==="

# CHECK 1: Determine entry path by need flags
NEEDS_DESIGN="[SESSION_PREFERENCES.need_flags.needs_design]"
echo "needs_design: $NEEDS_DESIGN"

if [ "$NEEDS_DESIGN" = "true" ]; then
  # CHECK 2 (needs_design): Design document must exist
  echo "Required: Design document exists"
  ls ~/.local/spellbook/docs/$PROJECT_ENCODED/plans/*-design.md 2>/dev/null || echo "FAIL: No design document found"

  # CHECK 3 (needs_design): Design review must be complete
  echo "Required: Design review completed"
else
  echo "Zero-flag fast path: no external design required"
  echo "Required: Inline plan confirmed by user (<=5 steps)"
  echo "Invoke /feature-implement-execute and navigate to its '## Phase 4: Implementation' header."
  echo "Skip the Phase 3 design-derived steps. Entering at Phase 4 directly."
fi

# CHECK 4 (all paths): No escape hatch conflict
echo "Verify: escape_hatch routing is consistent with current entry point"

If ANY check fails: STOP. Return to the appropriate phase.

Anti-rationalization: "Simple enough to hold in your head" or "plan as we go" = Pattern 3 (Time Pressure) or Pattern 5 (Competence Assertion). Implementation without a plan must be re-done.

Invariant Principles

  1. Design precedes implementation - Never implement without an approved design document and implementation plan
  2. Delegate actual work - Main context orchestrates; subagents write code, run tests, perform reviews
  3. Quality gates are mandatory - Code review, fact-checking, and green mirage audit after every task; no exceptions
  4. Behavior preservation in refactoring - Test verification at every transformation; no behavior changes without approval

Read the full file on GitHub · 293 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 · 293 lines · 28 tokens per session scan A 8b6ec6409675

Subscribe to this mod's changes

feature-implement is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 3,012 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.