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.
npx agentmods add commands/heznpc/ploidy/deprecategit clone --depth 1 https://github.com/heznpc/PLOIDYWrote 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.
[](https://agentmods.dev/commands/heznpc/ploidy/deprecate)<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>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 | $0.00046 | $0.00910 |
| Opus 5 | $0.00023 | $0.00455 |
| Sonnet 5 | $0.00009 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
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.
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:
- Why it exists — one sentence of the original motivation. State the year / quarter if you can.
- Who actually uses it today — concrete call sites, tests, external consumers. "Team uses it" is not enough; name the paths or endpoints.
- 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").
- Cost of keeping — enumerate: CI time, surface-area-cognitive load for new contributors, risk of stale dependencies, migration debt when the surrounding system changes.
- 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:
- What does this component do? State it in plain language.
- Is the problem it solves one that is still common in 2026?
- Are there obvious simpler / newer alternatives that solve the same problem? Name them generically.
- 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.
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.
- 4d ago First seen · 107 lines · 46 tokens per session scan A e8d746e6f5b4
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.