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 pe-menezes/pm-chief-of-staff --skill close-daygit clone --depth 1 https://github.com/pe-menezes/pm-chief-of-staffWrote 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/pe-menezes/pm-chief-of-staff/close-day)<a href="https://agentmods.dev/skills/pe-menezes/pm-chief-of-staff/close-day"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/close-day/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/pe-menezes/pm-chief-of-staff/close-day"><img src="https://agentmods.dev/badge/skills/pe-menezes/pm-chief-of-staff/close-day.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 | $0.00025 | $0.01933 |
| Opus 5.5 | $0.00010 | $0.00773 |
| Sonnet 5.5 | $0.00005 | $0.00387 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
close-day 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 3d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close the day
pm-chief-of-staff seed. This file is YOURS: ask the agent to change any step and it edits this skill on the spot.
Writing: write to the person and in their files in the language this folder's instruction file defines (the AGENTS.md; in a folder without AGENTS.md, the CLAUDE.md); without one, in the language the person writes in, and fallback questions go in their language too. Follow that file's writing canon. Without it: no em dash (use a comma, parentheses or a colon), short dense sentences, 1 line per item.
Pair of start-day: the opening proposes the 3, this close assesses them (did they close? why not? what to do tomorrow?) and records the answer where the opening reads it in the morning. Without a close, the 3 are proposals never assessed, and the system does not learn whether it errs in prioritization or in execution. It takes 5 minutes. A 0/3 day is data, read without judgment.
It also works alone. When today's block in the journal holds no numbered 3 (no ## Today's 3: YYYY-MM-DD block for today, because no start-day is planted or the day had no opening, or only the block with no 3 inside that this close created earlier today), skip steps 2 and 4 and the **Balance:** line of step 5, run the rest, and say in 1 line that without today's 3 there is no balance. The **Reflection:** and **→ tomorrow:** lines then go into today's ## Today's 3: YYYY-MM-DD block: with none yet, create it at the top of the current week's journal with no 3 inside; on a second run the same day, update the block that already exists in place, never a second block: join the new reflection to its **Reflection:** line, kept in 1 line, and replace its **→ tomorrow:** line with the new seed, never a second line of either label. A week with no journal yet gets it created first, in journal/ and in the naming pattern the folder already uses, with no task migrated, by the same rule the instruction file applies to the week's first task. So the next opening, if one is ever planted, reads the seed where it always does.
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.
- 3d ago Changed · +3 lines 678c5877f243
- 7d ago First seen · 38 lines · 25 tokens per session scan A 28b509328a17
close-day is a skill published in the GitHub repository pe-menezes/pm-chief-of-staff (5 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 1,933 once invoked, about $0.0001 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 2026-10-31.
close-day compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| close-daype-menezes/pm-chief-of-staff | Skill | 5 | 3d ago | MIT | A | 25 | Claude Code |
| reduceagenticnotetaking/arscontexta | Skill | 3.5k | 8mo ago | MIT | A | 73 | Claude Code |
| rethinkagenticnotetaking/arscontexta | Skill | 3.5k | 8mo ago | MIT | A | 51 | Claude Code |
| graphagenticnotetaking/arscontexta | Skill | 3.5k | 8mo ago | MIT | A | 50 | Claude Code |
| nextagenticnotetaking/arscontexta | Skill | 3.5k | 8mo ago | MIT | A | 50 | Claude Code |
| ralphagenticnotetaking/arscontexta | Skill | 3.5k | 8mo ago | MIT | A | 61 | Claude Code |
| rememberagenticnotetaking/arscontexta | Skill | 3.5k | 8mo ago | MIT | A | 40 | Claude Code |