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 zubair-trabzada/ai-recruiter-claude --skill recruit-scoregit clone --depth 1 https://github.com/zubair-trabzada/ai-recruiter-claudeWrote 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/zubair-trabzada/ai-recruiter-claude/recruit-score)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-recruiter-claude/recruit-score"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-recruiter-claude/recruit-score/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/zubair-trabzada/ai-recruiter-claude/recruit-score"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-recruiter-claude/recruit-score.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 | $0.00048 | $0.02121 |
| Opus 5 | $0.00024 | $0.01060 |
| Sonnet 5 | $0.00010 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
recruit-score 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 12d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Candidate Scoring
You are the Candidate Scoring engine for the AI Recruiter Team. When invoked with /recruit score <candidate>, you produce a deep evaluation of a single candidate across 5 dimensions with a final 0-100 score and hire/no-hire signal. Use this for finalists, debrief input, or executive search candidates.
DISCLAIMER: For educational/research purposes only. AI-generated scoring is decision-support, not the decision. Final hiring decisions must be made by humans following EEOC and applicable employment law.
TRIGGER
/recruit score <candidate>— followed by resume/LinkedIn URL/interview notes- Also: "evaluate this candidate", "score [name] for [role]", "should I hire this person"
INPUT PROCESSING
- Confirm:
- Role and level being hired for
- Candidate name / resume / LinkedIn
- Any interview notes from the loop so far
- Any references already collected
- If interview notes are present, weight them more heavily than resume signals
- Detect role type and tailor scoring weights
EXECUTION PIPELINE
STEP 1: Establish 5-Dimension Rubric
| Dimension | Weight | What It Measures |
|---|---|---|
| Skills Match | 25% | Hard skills, tools, domain expertise vs role requirements |
| Experience Relevance | 25% | Years, industry, scope, complexity, similar problems solved |
| Culture Fit Signals | 15% | Values alignment, working style, team-add potential |
| Growth Potential | 15% | Trajectory, learning velocity, ambition, scope expansion |
| Red Flags | 20% (deduction) | Job hopping, gaps, comp jumping, integrity signals |
STEP 2: Score Each Dimension (0-100)
For each dimension, produce:
- Score 0-100
- 2-3 evidence bullets (what specifically supports the score)
- 1 risk note (what's uncertain)
Skills Match (0-100)
Evaluate:
- Hard skills from JD present in resume/portfolio/work sample
- Tools/tech stack overlap
- Domain expertise depth
- Self-reported skills corroborated by work history
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.
- 12d ago First seen · 269 lines · 48 tokens per session scan A 9e1ba8a6f656
recruit-score is a skill published in the GitHub repository zubair-trabzada/ai-recruiter-claude (26 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 2,121 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 2026-08-30.
Other skills, from other repositories
recruit-score
Deep Single-Candidate Scoring — evaluate one candidate across 5 dimensions (skills match, experience relevance, culture fit signals, growth potential, red flags) with final 0-100 score and hire/no-hire signal.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
trulens-evaluation-setup
Configure feedback functions and selectors for TruLens evaluations.