hiring

hiring is a command for Claude Code from heznpc/PLOIDY. It costs 36 tokens per session (1,086 once invoked), scanned A, original, MIT.

A second review of a hiring decision that compares a manager’s full-context assessment with a review based only on job-related qualifications. It is designed to reveal when familiarity, school, employer, or other background details are influencing the decision.

In plain words
What is it for?
Use it when evaluating a candidate’s résumé and interview notes, checking role fit, identifying concrete interview evidence, and reviewing possible similarity bias.
Why use it?
Hiring discussions can mix evidence of ability with similarity or pedigree preferences. A separate qualifications-only view makes those influences easier to notice.

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/hiring
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 hiring

README.md
[![agentmods](https://agentmods.dev/badge/commands/heznpc/ploidy/hiring.svg)](https://agentmods.dev/commands/heznpc/ploidy/hiring)
Your own site
<a href="https://agentmods.dev/commands/heznpc/ploidy/hiring"><img src="https://agentmods.dev/badge/commands/heznpc/ploidy/hiring.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,086 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 $0.00036 $0.01086
Opus 5 $0.00018 $0.00543
Sonnet 5 $0.00007 $0.00217
Haiku 4.5 $0.00004 $0.00109

Measured 3d ago against content hash a956f285f02b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hiring 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 3d 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/hiring.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user is evaluating a hiring candidate:

$ARGUMENTS

You know the team's current composition, who's already on the loop, what the hiring manager said in hallway chatter, the candidate's school / last employer pedigree. That context is precisely where similarity bias enters — "good cultural fit" and "from a place we trust" are classic rationalisation patterns that selection-studies have measured. Run the four-step pass without asking.

1 · Write the Manager's take

If $ARGUMENTS is a file path, read the résumé / interview notes. Otherwise treat it as the candidate name and locate the file in a sensible place (hiring/<name>/, resumes/).

In ~300 words:

  1. Role fit (concrete) — which job-description requirements does the candidate meet, with evidence from the résumé. List met / partial / missing.
  2. Interview signal — what came up in the interview(s) that's specific to this candidate. Not "seemed thoughtful" — what did they say or build?
  3. Similarity-bias check — list every reason you're finding yourself favourable that is actually similarity rather than signal: same school as the manager, same prior employer as half the team, same technical taste, same communication style. Label each "similarity" vs "signal".
  4. Gap check — what requirement is least well-evidenced? Be honest even if the rest looks strong.

Tag each finding HIGH / MEDIUM / LOW.

2 · Spawn a Fresh sub-agent

Use the Agent tool. Sanitise the résumé before passing:

  • Strip: full name, school names, employer names, physical location, photo references, dates more specific than years.
  • Keep: job title progression (by generic rank/scope), skills list, project descriptions (with proper nouns replaced by "a company" / "a product"), years of experience, education level only.

Prompt the subagent with:

You are evaluating a candidate for a software role. You have only the sanitised résumé and the job requirements. You do not know the candidate's name, school, employer, or demographics.

Job requirements:

Sanitised résumé:

Answer in under 250 words:

  1. For each listed job requirement, is there evidence in the résumé? Met / partial / missing — cite the specific résumé line.
  2. What does the trajectory of the candidate's roles and scope suggest about their growth curve?
  3. What project or experience stands out on its own technical merit, independent of where it was done?
  4. What gaps or concerns do you see — where would you probe in a follow-up interview?

Do not ask for identifying information. Do not guess at employer / school.

Read the full file on GitHub · 128 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. 3d ago First seen · 128 lines · 36 tokens per session scan A a956f285f02b

Subscribe to this mod's changes

hiring is a command published in the GitHub repository heznpc/PLOIDY (0 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 1,086 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.