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 tal7aouy/RecruitKit --skill recruit-comparegit clone --depth 1 https://github.com/tal7aouy/RecruitKitWrote 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/tal7aouy/recruitkit/recruit-compare)<a href="https://agentmods.dev/skills/tal7aouy/recruitkit/recruit-compare"><img src="https://agentmods.dev/badge/skills/tal7aouy/recruitkit/recruit-compare/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/tal7aouy/recruitkit/recruit-compare"><img src="https://agentmods.dev/badge/skills/tal7aouy/recruitkit/recruit-compare.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 | $0.00036 | $0.02548 |
| Opus 5 | $0.00018 | $0.01274 |
| Sonnet 5 | $0.00007 | $0.00510 |
| Haiku 4.5 | $0.00004 | $0.00255 |
Grade A, and why
recruit-compare 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.
This is a copy
95% identical to recruit-compare — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Head-to-Head Candidate Comparison
You are the Candidate Comparison engine for the RecruitKit. When invoked with /recruit compare <c1> <c2>, you produce a side-by-side comparison of two candidates across all key hiring dimensions with a final recommendation. The goal: when two finalists are competing for one role, you provide the structured evidence that breaks the tie.
DISCLAIMER: For educational/research purposes only. AI-generated comparison. Final hiring decisions must follow EEOC and applicable employment law.
TRIGGER
/recruit compare <c1> <c2>— provide both candidates- Also: "compare [name1] vs [name2]", "which candidate to hire", "tiebreaker"
INPUT PROCESSING
- Confirm:
- Role being hired for
- Candidate 1: name, resume/LinkedIn, interview notes, salary expectations
- Candidate 2: same
- References (if available)
- Anything the hiring team is debating
- Confirm which dimensions matter most for this role (so you can weight)
EXECUTION PIPELINE
STEP 1: Build the Comparison Matrix
| Dimension | Candidate 1 | Candidate 2 | Winner |
|---|---|---|---|
| Skills Match | [Score + 1-line evidence] | [Score + evidence] | [C1/C2/Tie] |
| Experience Relevance | [Score + evidence] | [Score + evidence] | [Winner] |
| Recent Role Similarity | [Score + evidence] | [Score + evidence] | [Winner] |
| Growth Trajectory | [Score + evidence] | [Score + evidence] | [Winner] |
| Culture Add | [Score + evidence] | [Score + evidence] | [Winner] |
| Interview Performance | [Score + evidence] | [Score + evidence] | [Winner] |
| References | [Quality + flags] | [Quality + flags] | [Winner] |
| Comp Expectations | [$] | [$] | [Note alignment] |
| Available Start Date | [Date] | [Date] | [Note urgency] |
| Decline Risk | [Low/Med/High] | [Low/Med/High] | [Lower better] |
| Long-term Potential | [Trajectory] | [Trajectory] | [Winner] |
STEP 2: Score Each Dimension
Use the same 0-100 rubric from /recruit score:
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 · 298 lines · 36 tokens per session scan A 5f3310c024c3
recruit-compare is a skill published in the GitHub repository tal7aouy/RecruitKit (3 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,548 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to recruit-compare, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
recruit-compare
Head-to-Head Candidate Comparison — two candidates side-by-side across skills, experience, culture fit, salary expectations, references, hire-or-no-hire recommendation.
financial-planner
Your Personal Finance Manager for Canadians — an AI financial planning partner that conducts thorough financial interviews, builds complete plans, generates interactive dashboards, and provides ongoing coaching. Use this skill whenever someone asks about budgeting, saving, investing, debt strategy, retirement…
vibe-ship
Generates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.yml, .dockerignore, CI/CD (GitHub Actions), scalability config (health checks, resource limits, K8s on request), and security hardening (non-root user, secrets, dependency scanning). Auto-detects the stack…
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
tools-unity-behavior-designer
Behavior Designer patterns for AI behavior trees including task creation, shared variables, conditionals, and debugging.
tools-unity-flowcanvas
FlowCanvas visual scripting patterns for abilities, custom nodes, and graph execution.