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 skills add Xiaowen-Jiang/agent-enterprise --skill hiring_evaluationgit clone --depth 1 https://github.com/Xiaowen-Jiang/agent-enterpriseWrote 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/skills/xiaowen-jiang/agent-enterprise/hiring_evaluation)<a href="https://agentmods.dev/skills/xiaowen-jiang/agent-enterprise/hiring_evaluation"><img src="https://agentmods.dev/badge/skills/xiaowen-jiang/agent-enterprise/hiring_evaluation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xiaowen-jiang/agent-enterprise/hiring_evaluation"><img src="https://agentmods.dev/badge/skills/xiaowen-jiang/agent-enterprise/hiring_evaluation.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00014 | $0.00429 |
| Opus 5 | $0.00007 | $0.00215 |
| Sonnet 5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
Hiring Evaluation 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 9d 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.
What it actually says
Process
- Assess need: Why is a new hire needed? What gap does it fill?
- Check capacity: Review current team workload and performance scores
- Budget check: Verify token budget can support another agent
- Define the role: Specify responsibilities, required skills, and reporting line
- Make recommendation: Hire or don't hire, with justification
Evaluation Framework
Need Assessment
- What tasks are currently not being done or done poorly?
- Could an existing agent be retrained/reassigned instead?
- Is this a temporary need or ongoing?
Role Definition
- Title: Clear, descriptive role name
- Department: Where in the org chart
- Reports to: Which manager
- Archetype: Manager (can delegate) or Worker (executes)
- Key responsibilities: 3-5 bullet points
- Required tools: What MCP access they need
- Persona: Personality traits that would be effective
Budget Impact
- Token limit needed (default: 50,000)
- Expected daily usage
- Total company token budget impact
Output Format
Hiring Recommendation: [HIRE / DO NOT HIRE]
Proposed Role: [Title] Department: [Name] Reports to: [Manager name] Justification: [2-3 sentences]
Role Details:
- Responsibilities: ...
- Required tools: ...
- Suggested persona: ...
Budget Impact: [X tokens/session, Y% of company budget]
Guidelines
- Always check performance scores of current team first
- Prefer reassignment over new hire when possible (cost-effective)
- New managers should only be hired if span of control is too wide (>5 direct reports)
- Consider department balance — don't over-invest in one area
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.
- 9d ago First seen · 60 lines · 14 tokens per session scan A 009d26cd9dbd
Hiring Evaluation is a skill published in the GitHub repository Xiaowen-Jiang/agent-enterprise (52 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 429 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 2026-08-30.
Other skills, from other repositories
Applicant Screening
Screen job applications against requirements and score candidates.
Offer Letter Generator
Create formal employment offer letters with compensation and terms.
Job Description Generator
Generate professional, inclusive job descriptions that attract qualified candidates.
apply-merit-selection
Use when making any talent selection, promotion, or recommendation decision — to test your evaluation against the reversed-relationship check, because evaluator relationship bias systematically corrupts talent decisions even in well-intentioned evaluators, and merit discipline must be applied at the moment of…
write-job-description
Use when creating or improving a job posting, role description, or position specification to attract qualified candidates.
myers-briggs-type-indicator
Maps team cognitive diversity using the MBTI four-dichotomy personality framework: Extraversion/Introversion, Sensing/Intuition, Thinking/Feeling, Judging/Perceiving. Use when diagnosing co-founder communication friction, designing cognitively diverse teams, adapting communication style for different audiences…