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 anhnguyen0905/codex-mcp --skill hr-recruitinggit clone --depth 1 https://github.com/anhnguyen0905/codex-mcpWrote 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/anhnguyen0905/codex-mcp/hr-recruiting)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/hr-recruiting"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/hr-recruiting/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/anhnguyen0905/codex-mcp/hr-recruiting"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/hr-recruiting.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 | $0.00093 | $0.01254 |
| Opus 5 | $0.00046 | $0.00627 |
| Sonnet 5 | $0.00019 | $0.00251 |
| Haiku 4.5 | $0.00009 | $0.00125 |
Grade A, and why
hr-recruiting 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HR & Recruiting Operations (hiring pipeline, interviews, comp, people analytics)
Design the hiring process backwards from the decision
Before sourcing anyone, write down: the role's success criteria at 90 days and 12 months, the 4–6 competencies that predict them, and which pipeline stage tests each competency. A stage that tests nothing is theater; a competency tested nowhere is a coin flip at offer time.
Per stage, record: what it assesses | who assesses | pass bar | expected pass-through %
Structured interviews or noise
- Same questions, same order, per role. Unstructured "get to know them" interviews have near-zero predictive validity and maximize bias; structure is the single highest-leverage fix.
- Behavioral anchors, not gut scores. Each question gets a 1–4 rubric with written descriptions of what a 1 and a 4 look like. "Strong hire / hire / no hire" without anchors just launders intuition.
- Independent scoring first. Interviewers submit written scores before any debrief; the loudest voice in a live discussion otherwise sets everyone's number.
- Work samples beat questions. For any role where a realistic exercise exists, a scored work sample outpredicts every interview question about the same skill.
Pipeline metrics — definitions
pass-through(stage) = candidates advancing from stage / candidates entering stage
time-to-hire = days from candidate entering pipeline → offer accepted
time-to-fill = days from req opened → offer accepted (measures the process, not the person)
offer acceptance rate = offers accepted / offers extended
source yield = hires from source / candidates from source (compute per stage, per source)
cost per hire = (agency + ads + tooling + recruiter time) / hires in period
Read the funnel per role and per source. A 2% resume→hire yield is normal; the diagnostic value is in where it drops. A collapse at final stage means earlier stages don't test what the final bar tests (wasted interviewer hours); a collapse at offer means comp, close process, or speed.
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 · 104 lines · 93 tokens per session scan A f1a51b5cf7b1
hr-recruiting is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 1,254 once invoked, about $0.0005 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.