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 skills/hoavdc/codexkit/codexkit-talent-review-calibratornpx skills add hoavdc/CodexKit --skill codexkit-talent-review-calibratorgit clone --depth 1 https://github.com/hoavdc/CodexKitWrote 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/hoavdc/codexkit/codexkit-talent-review-calibrator)<a href="https://agentmods.dev/skills/hoavdc/codexkit/codexkit-talent-review-calibrator"><img src="https://agentmods.dev/badge/skills/hoavdc/codexkit/codexkit-talent-review-calibrator.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 | $0.00075 | $0.00653 |
| Opus 5 | $0.00037 | $0.00327 |
| Sonnet 5 | $0.00015 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
codexkit-talent-review-calibrator 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 yesterday.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talent Review Calibrator
Purpose
Support fairer and more actionable talent discussions by structuring evidence, risk, and development actions.
When to use
- Leaders are preparing a talent review or succession discussion.
- Managers need calibration before promotion or performance decisions.
- HR wants consistent talent cards and action plans.
When not to use
- The task is a transactional HR operation.
- There is no evidence beyond vague opinion or hearsay.
Inputs
- employee or talent pool list
- recent performance evidence and outcomes
- potential indicators, readiness signals, and role criticality
- retention risk, succession context, or capability gaps
Procedure
- Define the evaluation lens and remove criteria drift before rating people.
- Separate evidence, interpretation, and bias risks.
- Place talent using performance, potential, and readiness signals.
- Identify critical-role coverage, succession gaps, and flight risk.
- Recommend development, retention, promotion, or watch actions.
- Flag where calibration evidence is weak or inconsistent.
Output
- talent calibration summary
- per-person talent cards
- 9-box or equivalent placement rationale
- succession and retention risk view
- action plan with owners and timing
Definition of done
- Each recommendation ties back to evidence.
- Critical talent risks and succession gaps are visible.
- The output is usable in an actual calibration session.
Examples
- "Prepare a talent review pack for our engineering and operations managers."
- "Calibrate promotion readiness for these six employees and identify development actions."
Quality Criteria
- Feedback is specific and references exact locations in the reviewed material
- Each critique includes a concrete improvement suggestion
- Severity is categorized (critical / important / nice-to-have)
- Positive aspects are acknowledged alongside areas for improvement
Verification (4C)
| Check | Question |
|---|---|
| Correctness | Is the feedback technically accurate and properly contextualized? |
| Completeness | Were all major sections of the reviewed material addressed? |
| Context-fit | Is the review granularity appropriate for the material's maturity level? |
| Consequence | If the author implemented all feedback literally, what could go wrong? |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 85 lines · 75 tokens per session scan A e71c36a49dc0
codexkit-talent-review-calibrator is a skill published in the GitHub repository hoavdc/CodexKit (21 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 653 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
claude_code_delegation
Delegate coding, review, and refactor tasks to Claude Code CLI through Row-Bot's approval-gated shell workflow.
developer_review
Code-review workflow for Developer Studio repositories.
reducing-aigc-detection
Systematically reduce AIGC detection rates in academic papers (Chinese/English). Analyzes detection reports, identifies high-impact sections, applies multi-layer rewriting strategies preserving formatting/footnotes, and verifies results. Supports 维普/知网/Turnitin platforms.
architecting-security
安全架构与治理：威胁建模 (STRIDE/PASTA/LINDDUN)、零信任身份架构、IAM/SSO/MFA/PAM、合规框架 (SOC2/PCI/HIPAA/GDPR)、DLP、隐私工程、安全控制设计。Use when designing security architecture, threat modeling new systems, implementing zero-trust identity, designing IAM/SSO/PAM, building compliance evidence chains, or planning privacy-by-design.
defending-applications
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning…
detecting-and-responding
蓝队与紫队工程：检测规则编写、SIEM/EDR 调优、事件响应、数字取证、威胁狩猎、ATT&CK 映射、紫队演练闭环。Use when writing Sigma/YARA detection rules, tuning SIEM noise, responding to security incidents, conducting forensic analysis, hunting threats, or running purple team exercises.