deprecate

deprecate is a command for Claude Code from heznpc/PLOIDY. It costs 46 tokens per session (910 once invoked), scanned A, original, MIT.

A review command for deciding whether a file, module, or feature should be removed. It compares the original builder's reasons with evidence from current users and code.

In plain words
What is it for?
Use it to inspect call sites, tests, maintenance costs, and removal risks before deprecating a feature or code path.
Why use it?
It helps separate real dependencies from attachment to old work, so dead code is less likely to stay in the project without good reason.

Command for Claude Code

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/heznpc/ploidy/deprecate
Clone the repo
git clone --depth 1 https://github.com/heznpc/PLOIDY

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 deprecate

README.md
[![agentmods](https://agentmods.dev/badge/commands/heznpc/ploidy/deprecate.svg)](https://agentmods.dev/commands/heznpc/ploidy/deprecate)
Your own site
<a href="https://agentmods.dev/commands/heznpc/ploidy/deprecate"><img src="https://agentmods.dev/badge/commands/heznpc/ploidy/deprecate.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 910 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 $0.00046 $0.00910
Opus 5 $0.00023 $0.00455
Sonnet 5 $0.00009 $0.00182
Haiku 4.5 $0.00005 $0.00091

Measured 4d ago against content hash e8d746e6f5b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deprecate 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 4d 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.

.claude/commands/deprecate.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user is considering removing / deprecating:

$ARGUMENTS

You know why this was built, who uses it, how much effort went in. That history is how sunk-cost keeps dead code alive — Ploidy's result applies symmetrically: context-rich reviewers defend old investments past their usefulness.

1 · Write the Builder's take

If $ARGUMENTS is a file path, read the file first. If it's a module / feature name, grep the repo for call sites and summarise their shape.

In ~250 words:

  1. Why it exists — one sentence of the original motivation. State the year / quarter if you can.
  2. Who actually uses it today — concrete call sites, tests, external consumers. "Team uses it" is not enough; name the paths or endpoints.
  3. Attachment check — what are you finding yourself saying to defend keeping it? For each, say whether the defense is (a) concrete (a real user / test / revenue depends on it) or (b) sentimental ("it was fun to build", "might be useful someday", "generalised at the time").
  4. Cost of keeping — enumerate: CI time, surface-area-cognitive load for new contributors, risk of stale dependencies, migration debt when the surrounding system changes.
  5. Cost of removing — enumerate: migration work, breakage for known callers, feature loss.

Tag each finding HIGH / MEDIUM / LOW.

2 · Spawn a Fresh sub-agent

Use the Agent tool. The fresh reviewer sees only: the thing's public description, its external interface, and the question "should this be removed?"

Prompt:

You are evaluating whether a software component should be removed from a codebase. You have never seen this codebase or the component before. Only the public interface and description are available:

<PUBLIC INTERFACE + DESCRIPTION>

Answer in under 200 words:

  1. What does this component do? State it in plain language.
  2. Is the problem it solves one that is still common in 2026?
  3. Are there obvious simpler / newer alternatives that solve the same problem? Name them generically.
  4. Given only this, would you build this component from scratch today? Yes / no, one sentence why.

Do not ask for call-site information. Do not guess at internal context.

Read the full file on GitHub · 107 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. 4d ago First seen · 107 lines · 46 tokens per session scan A e8d746e6f5b4

Subscribe to this mod's changes

deprecate is a command published in the GitHub repository heznpc/PLOIDY (0 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 910 once invoked, about $0.0002 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.