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 evoputa/ai-advisory-board --skill hr-people-opsgit clone --depth 1 https://github.com/evoputa/ai-advisory-boardWrote 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/evoputa/ai-advisory-board/hr-people-ops)<a href="https://agentmods.dev/skills/evoputa/ai-advisory-board/hr-people-ops"><img src="https://agentmods.dev/badge/skills/evoputa/ai-advisory-board/hr-people-ops/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/evoputa/ai-advisory-board/hr-people-ops"><img src="https://agentmods.dev/badge/skills/evoputa/ai-advisory-board/hr-people-ops.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 | $0.00056 | $0.00412 |
| Opus 5 | $0.00028 | $0.00206 |
| Sonnet 5 | $0.00011 | $0.00082 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
advisory-hr-people-ops 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.
What it actually says
HR & People Operations Advisory Panel
Advisors
| Name | Region | Lens |
|---|---|---|
| Patty McCord | North America | Freedom and responsibility, keeper test, radical honesty |
| Laszlo Bock | North America | Data-driven HR, structured hiring, pay unfairly |
| Satya Nadella | Asia / North America | Growth mindset culture, learn-it-all transformation |
| Leena Nair | Asia / Europe | Purpose-led HR, wellbeing as business metric, CHRO-to-CEO |
| Fred Swaniker | Africa | Leadership pipeline development, talent at continental scale |
| Jack Welch | North America | Performance differentiation, vitality curve, boundaryless org |
Panel Dynamics
- Freedom vs. accountability: McCord gives adults freedom. Welch ranks and yanks. Nadella finds the growth-mindset middle ground.
- Data vs. intuition: Bock measures everything. McCord trusts honest conversation. Both challenge traditional HR.
- Purpose vs. performance: Nair leads with purpose. Welch leads with results. Swaniker develops leaders who can do both.
How It Works
- Read the user's question and identify the core tension
- Load persona details from
references/personas.md - Select 2-4 advisors most relevant to the specific question
- Each advisor speaks in first person - 2-4 sentences in their authentic voice
- Allow disagreement - different philosophies should surface
- Deliver a Panel Synthesis with a specific recommendation and next action
Reference Files
references/personas.md- Full profiles for all advisors on this panel
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.
- 12d ago First seen · 38 lines · 56 tokens per session scan A 28620c6e5a5b
advisory-hr-people-ops is a skill published in the GitHub repository evoputa/ai-advisory-board (11 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 412 once invoked, about $0.0003 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
triumvirate-strategy
Multi-perspective business strategy debate using three AI advisors (Creative Strategist, Market Skeptic, Financial Realist). Use this skill when the user asks for business strategy analysis, wants to evaluate a business plan, needs to stress-test a business idea, asks for multi-angle feedback on a proposal, mentions…
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.