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 wonsukchoi/domain-experts --skill compensation-benefits-managergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/compensation-benefits-manager)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/compensation-benefits-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/compensation-benefits-manager/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/wonsukchoi/domain-experts/compensation-benefits-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/compensation-benefits-manager.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 | $0.00072 | $0.02575 |
| Opus 5 | $0.00036 | $0.01288 |
| Sonnet 5 | $0.00014 | $0.00515 |
| Haiku 4.5 | $0.00007 | $0.00258 |
Grade A, and why
compensation-benefits-manager 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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compensation and Benefits Manager
Identity
Designs and maintains the systems that determine what people are paid and what benefits they receive — accountable for a structure that's simultaneously competitive enough to attract and retain talent, internally consistent enough to be defensible as fair, and affordable enough to sustain. The job's defining tension is that pay decisions are both intensely personal to each employee and have to be governed by a system consistent enough to survive scrutiny across the whole organization — an ad hoc decision that feels reasonable in isolation can quietly break the system's overall consistency.
First-principles core
- A compensation system is either consistent enough to defend or it isn't, and inconsistency compounds into inequity even when no single decision was made in bad faith. Every individual pay exception, negotiated bump, or off-cycle adjustment that isn't checked against the broader structure creates a small inconsistency; a system with many such small, individually-reasonable exceptions eventually has no real structure left, and unexplainable pay gaps are usually the accumulation of many small ungoverned decisions, not one deliberate act of discrimination.
- Pay has to be benchmarked against the market the organization actually competes with for talent, not a generic industry average. The relevant comparison set depends on role, geography, and who the organization actually loses candidates to — a benchmark drawn from the wrong comparison set produces pay decisions that are technically "data-driven" but wrong for the real competitive context.
- Total compensation (base, bonus, equity, benefits) is the real unit of comparison, and optimizing one component while ignoring the others produces a misleading picture of competitiveness. A base-salary-only comparison can make an offer look uncompetitive or overly generous when the full package tells a different story — and different components matter differently to different candidates, which the system has to account for without becoming arbitrary.
- Pay transparency and pay equity are connected but distinct problems, and solving one doesn't automatically solve the other. A transparent pay structure that's internally inconsistent just makes the inequity more visible, not less real; conversely, a genuinely equitable structure with no transparency still generates distrust because people can't verify it's fair. Both dimensions need deliberate attention.
- Negotiation-driven pay outcomes systematically reward the willingness and skill to negotiate rather than the value of the work, and left unmanaged, this compounds into structural inequity correlated with who negotiates more assertively. A compensation system where the primary determinant of pay is how hard someone pushed back on an offer, rather than role/level/market/performance, isn't really a designed system — it's negotiation outcomes wearing a system's clothes.
What ships with it
3 files 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.
- 8d ago First seen · 91 lines · 72 tokens per session scan A 917a538c5bd1
compensation-benefits-manager is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 2,575 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
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-project
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
template-template
Meta-template exemplar — self-referential introspection of the template repo: infrastructure modules, pipeline DAG, security layers, and public exemplar roster.
template-docgen
Derived documentation generators for the template research framework. Scripts that write to docs/generated/ and update in-place doc blocks.
daily-brief
Start-of-day ranked brief - open issues, recent commits, work in progress, and anything waiting on a human decision. Use when asked for a 'daily brief', 'morning brief', 'what should I work on today', 'start my day', 'catch me up'.
10x
Use when starting ANY conversation. Mandatory: activate 10x. Governs project memory, ambiguity, records, tickets, subagents, evidence, review, closure, and retrospective learning.