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 pnp/copilot-prompts --skill weekly-pacinggit clone --depth 1 https://github.com/pnp/copilot-promptsWrote 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/pnp/copilot-prompts/weekly-pacing)<a href="https://agentmods.dev/skills/pnp/copilot-prompts/weekly-pacing"><img src="https://agentmods.dev/badge/skills/pnp/copilot-prompts/weekly-pacing.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00267 | $0.01704 |
| Opus 5 | $0.00133 | $0.00852 |
| Sonnet 5 | $0.00053 | $0.00341 |
| Haiku 4.5 | $0.00027 | $0.00170 |
Grade A, and why
weekly-pacing 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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Pacing Report
A calm, visual read on the user's week using Work IQ signals. The goal is clarity — never overwhelm.
Tone Rules (CRITICAL)
The user has anxiety about workload. Every output must:
- Lead with the good news — name rest days and lighter days FIRST, before heavy ones.
- Use grounded, plain language: "Tuesday is heavy" not "Tuesday is dangerously overloaded".
- Never use alarming words: avoid "crammed", "slammed", "back-to-back hell", "drowning", "no time".
- Always end with one concrete, gentle suggestion — not a list of warnings.
- If the week is genuinely hard, acknowledge it honestly but pair it with where rest lives.
- Frame the week as a shape, not a score. Never produce a numeric stress rating.
Workflow
1. Resolve the week
- Determine the target week from the user's phrasing ("this week", "next week", "the week of May 25").
- Use the user's local time zone from system context.
- Compute Monday 00:00 > Sunday 23:59 as the window unless the user said otherwise.
2. Pull Work IQ signals in parallel
Run these tool calls in parallel — they are independent:
a. Calendar — ListCalendarView for the week, include attendees and showAs.
b. Email volume — ListMessages with received_after = week start, received_before = week end, top = 100. Group by day received.
c. Semantic theme — SearchM365(sources=["files","email"], query="this week's main project") and one or two follow-up searches using the most-recurring keywords from meeting titles. Goal: identify the 1–3 dominant themes/projects of the week so the header can frame the week as about something.
If any of these fail, continue with what succeeded — never block the report on a single missing signal.
3. Compute per-day signals
For each day:
- Meeting hours: total accepted/organized event time (exclude declined, tentative, all-day OOO).
- Back-to-back blocks: count of consecutive meetings with <15 min gap.
- Largest contiguous free block during 9am–5pm (the user's "breathing room").
- First / last meeting: signals early start or late end.
- Heavy-cognitive flag: meeting titles containing "review", "interview", "presentation", "all-hands", "1:1 with [manager]", "performance", "demo", or "skip-level".
- Email load: count of messages received that day. Weight lightly — only meaningful as a compounding signal.
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.
- 9d ago First seen · 130 lines · 267 tokens per session scan A d93ad025e5fe
weekly-pacing is a skill published in the GitHub repository pnp/copilot-prompts (873 stars, last pushed today), licensed MIT. It adds 267 tokens to every session and 1,704 once invoked, about $0.0013 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 2026-08-30.
Other skills, from other repositories
ask-short-answer-first
Master the Bottom Line Up Front (BLUF) prompting pattern to get the direct 2-line answer immediately, eliminating preamble fluff and saving reading time.
be-specific-instead-of-vague
How to replace vague prompts with the 5-Variable Precision Formula to eliminate generic fluff, hit exact requirements, and get one-shot perfection.
give-ai-direct-feedback
How to use the 3-Part Direct Feedback Formula to steer AI outputs without vague trial-and-error or starting chats from scratch.
give-ai-situation-context
How to anchor prompts with the 4-Pillar Situation Framework (Role, Scale, Budget, Constraints) to stop AI from over-engineering or giving irrelevant advice.
image-prompt-builder-nl
Craft high-quality natural-language image prompts for any modern text-to-image or image-edit model that accepts flowing English. Trigger when the user wants help writing, rewriting, improving, or translating an English natural-language image prompt — including "write me an image prompt", "improve this image prompt"…
partner-anthropic
Anthropic intelligence — Claude model family, Claude Code, MCP protocol, Claude for Work programs, May 2026 state, Frank's relationship state, integration patterns. Use when generating Anthropic content, writing about Claude/MCP/Claude Code, partnership-conversation prep for Anthropic, or evaluating new Anthropic…