dead-code-implement

A command for removing code that a separate report has identified as unused. It asks for approval before each deletion or deletion group and checks that existing behavior remains intact.

In plain words
What is it for?
Use it after a dead-code report to review, delete, and test unused code in dependency order.
Why use it?
It turns an unused-code report into controlled cleanup, reducing the risk of deleting code that another part of the project still needs.

Command

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 commands/axiomantic/spellbook/dead-code-implement
Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 748 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 $0.00016 $0.00748
Opus 5 $0.00008 $0.00374
Sonnet 5 $0.00003 $0.00150
Haiku 4.5 $0.00002 $0.00075

Measured yesterday against content hash a81bc96b405b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dead-code-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 yesterday.

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/dead-code-implement.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MISSION

Apply dead code deletions from /dead-code-report findings with explicit user approval.

Part of the dead-code- command family.* Run after /dead-code-report completes.

Prerequisites: Report generated with implementation plan.

Invariant Principles

  1. Never delete without approval - Explicit user consent via AskUserQuestion required for every deletion
  2. Follow dependency order - Delete dependents before dependencies
  3. Incremental verification - Run tests after each deletion batch
  4. Preserve functionality - All existing behavior must remain intact

Phase 7: Implementation Prompt

After presenting report, ask:

Found N items (N lines) of dead code.

Would you like me to:
A. Remove all dead code automatically (I'll create commits)
B. Remove items one-by-one with your approval
C. Create a cleanup branch you can review
D. Just keep the report, you'll handle it

Choose A/B/C/D:

If User Chooses A or B

Follow the writing-plans skill pattern. For each deletion in the ordered plan:

  1. Show code to be removed (exact lines, location)
  2. Show grep verification it's unused (paste output)
  3. Apply deletion
  4. Re-verify with grep (confirm no references remain)
  5. Ask: "Run tests now?" — run if yes, then proceed
  6. Commit after each Phase group from the implementation plan (e.g., "Phase 1: Simple Deletions")
  7. Final verification (after all deletions): Run full test suite; report results. Verify no new dead code was introduced by the cleanup.

Read the full file on GitHub · 93 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. yesterday First seen · 93 lines · 16 tokens per session scan A a81bc96b405b

Subscribe to this mod's changes

dead-code-implement is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 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 2026-08-31.