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/hiringgit 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/hiring)<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>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 | $0.00036 | $0.01086 |
| Opus 5 | $0.00018 | $0.00543 |
| Sonnet 5 | $0.00007 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
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.
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:
- Role fit (concrete) — which job-description requirements does the candidate meet, with evidence from the résumé. List met / partial / missing.
- Interview signal — what came up in the interview(s) that's specific to this candidate. Not "seemed thoughtful" — what did they say or build?
- 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".
- 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:
- For each listed job requirement, is there evidence in the résumé? Met / partial / missing — cite the specific résumé line.
- What does the trajectory of the candidate's roles and scope suggest about their growth curve?
- What project or experience stands out on its own technical merit, independent of where it was done?
- 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.
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.
- 3d ago First seen · 128 lines · 36 tokens per session scan A a956f285f02b
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.