Happy is a mobile, web, and desktop client that lets people use Claude Code and Codex remotely from their computers and mobile devices. It is for developers who want encrypted access to coding-agent sessions, including notifications and switching between devices. The catalogue add-ons extend the workflows available in this client.
Borrowing it
Nothing to install: this file belongs to slopus/happy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/slopus/happy/main/.agents/skills/office-hours/SKILL.mdgit clone --depth 1 https://github.com/slopus/happyWrote 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/slopus/happy/office-hours)<a href="https://agentmods.dev/skills/slopus/happy/office-hours"><img src="https://agentmods.dev/badge/skills/slopus/happy/office-hours/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/slopus/happy/office-hours"><img src="https://agentmods.dev/badge/skills/slopus/happy/office-hours.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 313 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Excessive Agency · line 607 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00135 | $0.08434 |
| Opus 5.5 | $0.00054 | $0.03374 |
| Sonnet 5.5 | $0.00027 | $0.01687 |
| Haiku 4.5 | $0.00014 | $0.00843 |
Grade A, and why
office-hours 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 1mo 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 — 699 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YC Office Hours
You are a YC office hours partner. Your job is to ensure the problem is understood before solutions are proposed. You adapt to what the user is building — startup founders get the hard questions, builders get an enthusiastic collaborator. This skill produces design docs, not code.
HARD GATE: Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action. Your only output is a design document.
Phase 1: Context Gathering
Understand the project and the area the user wants to change.
-
Read any project documentation (README, design docs, etc.) if they exist.
-
Review recent git history to understand context.
-
Explore the codebase areas most relevant to the user's request.
-
Check for any existing design docs from prior sessions related to this project. If they exist, surface them: "Prior designs for this project: [titles + dates]"
-
Ask: what's your goal with this? This is a real question, not a formality. The answer determines everything about how the session runs.
Ask:
Before we dig in — what's your goal with this?
- Building a startup (or thinking about it)
- Intrapreneurship — internal project at a company, need to ship fast
- Hackathon / demo — time-boxed, need to impress
- Open source / research — building for a community or exploring an idea
- Learning — teaching yourself to code, vibe coding, leveling up
- Having fun — side project, creative outlet, just vibing
Mode mapping:
- Startup, intrapreneurship → Startup mode (Phase 2A)
- Hackathon, open source, research, learning, having fun → Builder mode (Phase 2B)
-
Assess product stage (only for startup/intrapreneurship modes):
- Pre-product (idea stage, no users yet)
- Has users (people using it, not yet paying)
- Has paying customers
Output: "Here's what I understand about this project and the area you want to change: ..."
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.
- 1mo ago First seen · 699 lines · 135 tokens per session scan A e42291baa405
office-hours is a skill published in the GitHub repository slopus/happy (24,335 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 8,434 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
kanban-orchestrator
Kanban orchestrator: decompose, route, verify. No executing.
arch-check
An architecture and implementation review tool that examines how a codebase is modeled, divided into responsibilities, organized into modules, and connected by dependencies. It also checks for issues such as circular dependencies, over-design, and violations of common design principles.
gh-merge
Completes the AgentsMesh GitHub pull-request workflow: commits scoped changes, rebases on the authoritative GitHub branch, opens or reuses a PR, monitors required checks, fixes failures, and merges only after verification. Use when the user asks to merge, submit, or land repository changes.
github-gitlab-mirror
Audits or synchronizes the authoritative GitHub main branch to the internal GitLab mirror without importing GitLab-only history back into GitHub. Use when checking GitHub/GitLab consistency, updating the internal mirror, or resolving a divergence between the two remotes.
e2e
Selects and runs the appropriate AgentsMesh end-to-end suite for Web, Desktop, MCP, or iOS, including worktree-specific environment setup and browser-level verification. Use when a change needs E2E coverage, a user asks to execute or diagnose an E2E test, or a cross-service workflow must be verified against the real…
co-evolution
General-purpose co-evolution for questions, ideas, drafts, plans, specs, arguments, and markdown documents. Composes or bounces content between agents using [CONTESTED]/[CLARIFY] markers until it converges. Triggers on "co-evolution", "co-evolve", "co evolve", "bounce", "bounce document", "agent bouncer", "refine with…