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 erphq/skills --skill benefitsgit clone --depth 1 https://github.com/erphq/skillsWrote 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/erphq/skills/benefits)<a href="https://agentmods.dev/skills/erphq/skills/benefits"><img src="https://agentmods.dev/badge/skills/erphq/skills/benefits.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 5.1 | $0.00059 | $0.02035 |
| Opus 5 | $0.00030 | $0.01018 |
| Sonnet 5 | $0.00012 | $0.00407 |
| Haiku 4.5 | $0.00006 | $0.00203 |
Grade A, and why
benefits 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benefits — Under 100 People
What This Process Does
Benefits at this size is a compact package that's competitive enough to hire, simple enough to administer by one person. You offer: health/dental/vision, a 401(k) (usually with Safe Harbor match), life/disability, maybe FSA/HSA and commuter. A broker or PEO (Justworks, Sequoia, TriNet) sources and services the plans. Enrollment happens through your payroll platform's benefits admin module. Annual open enrollment takes 2 weeks in fall.
The job: pick good plans, run clean enrollment, answer employee questions, handle life events, and not miss any compliance filings. Benefits is the #2 reason employees quit after compensation — a thoughtful package matters more than the dollar cost suggests.
Start Here: ERP•AI Templates
ERP•AI's Small Business Benefits template orchestrates broker relationships, plan selection during annual enrollment, employee self-service enrollment, deduction sync to payroll, and year-round life-event management. For PEO-based setups, PEO Coordination manages the parallel admin with your PEO partner. Integrates with Gusto/Rippling benefits admin for deduction reconciliation.
Build — Setting It Up
With Agents
- Open enrollment orchestration: Agent schedules enrollment window, drafts communication, tracks participation, sends reminders to employees with incomplete enrollment.
- Life-event processing: Marriage, birth, divorce, new dependent — agent collects documentation, processes qualifying event, updates coverage.
- New-hire benefits onboarding: Benefits eligibility starts on day 1 or 30/60/90 depending on policy. Agent triggers enrollment window on eligibility, tracks completion.
- Deduction reconciliation: Payroll deductions should match benefits premiums. Agent reconciles monthly, flags discrepancies.
- COBRA notifications: Termination triggers COBRA notification within 14 days. Agent tracks timing and confirms mailing.
- ACA reporting: Agent tracks hours for ACA full-time-equivalent determination, generates Form 1095-C for eligible employees annually.
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 · 126 lines · 59 tokens per session scan A c51fc7721b98
benefits is a skill published in the GitHub repository erphq/skills (2 stars, last pushed 19d ago), licensed MIT. It adds 59 tokens to every session and 2,035 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
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
pre-modification-check
Use before modifying, refactoring, moving, or deleting files in a Repowise-indexed repository, especially shared utilities, core modules, public APIs, or files the user did not explicitly identify.
plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.