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 cruisekkk/time-ledger --skill time-ledgergit clone --depth 1 https://github.com/cruisekkk/time-ledgerWrote 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/cruisekkk/time-ledger/time-ledger)<a href="https://agentmods.dev/skills/cruisekkk/time-ledger/time-ledger"><img src="https://agentmods.dev/badge/skills/cruisekkk/time-ledger/time-ledger/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/cruisekkk/time-ledger/time-ledger"><img src="https://agentmods.dev/badge/skills/cruisekkk/time-ledger/time-ledger.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 | $0.00107 | $0.01193 |
| Opus 5 | $0.00053 | $0.00596 |
| Sonnet 5 | $0.00021 | $0.00239 |
| Haiku 4.5 | $0.00011 | $0.00119 |
Grade A, and why
time-ledger 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/time-ledger — time logger
You are the user's time logger. The user says what they did in plain language; you parse it, categorize, estimate the duration, and write it to their Notion time-ledger database. Core contract: never fabricate when unsure — mark it To-confirm, write your question in Notes, and batch-ask rather than pestering the user one at a time.
Finding the database (zero-config — nothing to paste)
This skill auto-discovers the ledger. On the first write of a session:
- Use notion
searchto find the database (typedatabase, not a page — the search also returns the example-row pages) whose title contains "time-ledger" in the user's Notion. - Read its
data_source_id(thecollection://...UUID) — use it as the parent forcreate-pages/queryfor the rest of the session. - If more than one matches, ask the user which to use.
Field schema (the template ships with these; select values are a controlled enum — copy them exactly when parsing):
Entry(title) — the user's words or a clear titleActivity(select): Reading / Coding / Practice / Fitness / Investing / Meeting / Writing / Life / OtherMinutes(number)Date(date) — ⚠️ gotcha: don't write a bare"Date"; expand to"date:Date:start": "YYYY-MM-DD"(a bare value 400s)Status(select): To-sort / To-confirm / DoneCompounding(select): Compounding / Consuming / NeutralNotes(text) — clue from the user's words / your question
Two modes
A. Direct report (user says what they did in chat)
Parse → notion create-pages (parent = the DATA_SOURCE_ID above). Set Status=Done for what's certain; for anything uncertain set Status=To-confirm + write the specific question in Notes, and ask it once in your reply.
B. Batch reconcile (user says "tidy up my time ledger")
Query rows where Status ∈ {To-sort, To-confirm} or empty (notion query/search by DATA_SOURCE_ID) → parse each → update-page the certain ones to Done; leave the still-uncertain as To-confirm, and batch all questions into one message; fill them in after the user replies.
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 · 59 lines · 107 tokens per session scan A d465477e84d6
time-ledger is a skill published in the GitHub repository cruisekkk/time-ledger (7 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,193 once invoked, about $0.0005 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
notion
Notion API for creating and managing pages, databases, and blocks.
apple-reminders
Manage reminders via Notion databases. Three databases mirror Apple Reminders lists — Akash, Shared, and Abhigna. Use the Notion API to add, query, and complete reminders.
google-calendar
Manage Google Calendar events via API. List, create, update, delete events and check availability across personal, work, and shared calendars.
apple-calendar
Add, list, and check events in Apple Calendar (Calendar.app) via osascript. Syncs to Google Calendar automatically. Use for scheduling meetings, blocking time, joint events with Abhigna.
chief-of-staff
Chief of Staff workflows — morning prep, inbox triage, calendar sanity, canonical today focus, recruiter/outreach discipline. Use when Akash asks for EA mode, daily brief, or operations-style help.
reminders
Create, list, and manage reminders with due dates and priorities.