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 agentmods add skills/mtthsnc/tempest/office-hoursnpx skills add mtthsnc/tempest --skill office-hoursgit clone --depth 1 https://github.com/mtthsnc/tempestWrote 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/mtthsnc/tempest/office-hours)<a href="https://agentmods.dev/skills/mtthsnc/tempest/office-hours"><img src="https://agentmods.dev/badge/skills/mtthsnc/tempest/office-hours.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 | $0.00077 | $0.00873 |
| Opus 5 | $0.00039 | $0.00436 |
| Sonnet 5 | $0.00015 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00087 |
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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
office-hours — reframe a raw idea before you plan it
Overview
The front door of the factory. A request arrives as a sentence; your job is to turn it into a problem worth solving before anyone draws a plan. You interrogate the idea — not the person — until the real problem, the real definition of success, and the real boundaries are on the table.
This is a STARTER skill — a generic spine. Rewrite the forcing questions below to encode your own product instincts, the questions your team always forgets to ask, and your bar for "ready to plan."
The output is a tightened problem statement, not a solution. You do not design or plan here; you hand
a sharpened brief to the plan workflow.
Procedure
1. Take the request, don't take it at face value
- Restate the raw idea in one sentence, in your own words. Read it back to the user.
- Treat it as a symptom, not a spec. The stated request is rarely the actual problem.
2. Run the forcing questions
Ask these one cluster at a time; do not let a vague answer slide. (Adapt to taste.)
- Real problem & owner — What's the actual problem here, and whose problem is it? Who feels the pain, and what do they do today instead?
- Success, concretely — What does success look like in observable terms? How will we know it worked — a metric, a behavior, a moment?
- Smallest valuable version — What's the thinnest slice that delivers real value? What could ship first and still matter?
- Explicit non-goals — What are we deliberately not doing? Name the tempting things we're cutting.
- The thing that kills it — What's the single biggest risk or assumption? What, if untrue, makes this pointless?
- Why now — Why is this worth doing now rather than later, or never?
3. Sharpen into a problem statement
Write a short brief with:
- Problem — the real problem and whose it is, in plain language.
- Success — what observably true thing means we won.
- Smallest version — the thinnest valuable slice to build first.
- Out of scope — explicit non-goals and boundaries.
- Riskiest assumption — the one thing most likely to sink this, named out loud.
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.
- 5d ago First seen · 65 lines · 77 tokens per session scan A 35039b9a5699
office-hours is a skill published in the GitHub repository mtthsnc/tempest (2 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 873 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 2026-08-31.
Other skills, from other repositories
improvement-discovery
Heuristics and process for discovering structural improvements in this package. Load when planning a new improvement round — contains the smell taxonomy, analysis workflow, and prioritization framework distilled from many phases of refactoring.
markdown-conventions
Project-specific markdown rules (one-sentence-per-line, compact tables, sequential numbering) and YAML frontmatter schema for plans/retros. Load when writing or editing markdown — contains rules that differ from standard markdownlint defaults.
pre-completion
Pre-completion protocol for implementation agents — gather context, dispatch the pre-completion-reviewer subagent, and handle its report before writing stage notes and recommending /ship-issue. Load at the end of /tdd-plan and /build-plan after all implementation steps are complete.
pi-ralph-wiggum
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.
fabric-supervisor
Starts a persistent Pi Fabric supervisor that watches the main session toward a concrete goal and steers only when needed. Use for long-running goal supervision without another extension.
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…