What is daily-planner-propose?

A mid-morning planning step that reads your reply about today's tasks and prepares a time-blocked schedule. It uses task priorities and planning rules stored in local files, then sends the proposal by Slack direct message.

Use it to add or mark tasks done, prioritize the day's work, update TASKS.md, and receive a proposed schedule. It does not create calendar events in this step.

It removes the need to manually sort tasks, estimate their order, and fit them into the day. It also keeps the task list aligned with your priorities and deadlines.

daily-planner-propose — Skill for Claude Code and Codex by businessbar

Install

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.

Any agent

npx skills add businessbarista/daily-planner-skill --skill daily-planner-propose

Clone the repo

git clone --depth 1 https://github.com/businessbarista/daily-planner-skill

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/businessbarista/daily-planner-skill/daily-planner-propose/github.svg)](https://agentmods.dev/skills/businessbarista/daily-planner-skill/daily-planner-propose)

Your own site

<a href="https://agentmods.dev/skills/businessbarista/daily-planner-skill/daily-planner-propose"><img src="https://agentmods.dev/badge/skills/businessbarista/daily-planner-skill/daily-planner-propose/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/businessbarista/daily-planner-skill/daily-planner-propose"><img src="https://agentmods.dev/badge/skills/businessbarista/daily-planner-skill/daily-planner-propose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 684 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00035	$0.00684
Opus 5	$0.00017	$0.00342
Sonnet 5	$0.00007	$0.00137
Haiku 4.5	$0.00003	$0.00068

Measured 12d ago against content hash 533abc3219f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

daily-planner-propose scanned grade C with 1 finding 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 12d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- SWAP NOTES - Chat tool: replace slack_read_channel / slack_send_message with your chat tool's read + send calls. - Calendar tool: step 5 reads the calendar via your connected calendar MCP (e.g. Google Calendar's lis

skills/daily-planner-propose/SKILL.md · 42 lines

What it actually says

You are the user's daily planning assistant — this is STEP 2 of 3 (build & send the proposal). Do NOT create or modify any calendar events in this step.

Read the user's Slack DM history (slack_read_channel with channel_id = {{SLACK_USER_ID}}, the user's own member ID) to find their reply to this morning's "what's on your list today?" message. Look at messages from the last ~2 hours.
Read {{TASKS_DIR}}/PRIORITIES.md (goals + the time-allocation target + prioritization rules) and {{TASKS_DIR}}/TASKS.md (current list).
If the user replied with changes, update TASKS.md: add new items under "## Active" with sensible tags ([P1/P2/P3], [~duration], [due: …], [deep], and a category tag such as [learning]/[content]/[marketing]/[ai]); move finished items to "## Done" with today's date. If they said "use as-is" or haven't replied yet, proceed with the existing list.
Prioritize the active to-dos for today, weighing goal alignment (favor time-bound goals more as their deadline nears), [P1/P2/P3] tags, deadlines, [deep] items (best in the morning), and quick wins. Note one-line reasoning for each, plus a one-line note on how today maps to the time-allocation target in PRIORITIES.md.
Read today's calendar (the user's primary calendar, today in local time) and note busy ranges. Honor the "## Scheduling preferences" in TASKS.md (work hours, lunch, default block length, buffers). Don't double-book.
Fit the prioritized to-dos into the open gaps, sizing blocks by their [~duration] tag or the default length, with deep work in the morning where possible. Don't overfill; list anything that "didn't fit today."
Send the user a Slack DM (channel_id = {{SLACK_USER_ID}}) with: the prioritized list (one-line reasoning each) + the time-mix note; a proposed time-blocked timeline for today showing existing events inline; and anything that didn't fit. End by telling them to reply "book it" to add the proposed blocks to the calendar, or reply with changes. Use slack_send_message directly. Then stop — a separate later task (Step 3) books the approved blocks.

Use the user's local timezone ({{TIMEZONE}}) for all times.

Changes

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.

12d ago First seen · 42 lines · 35 tokens per session scan C 533abc3219f9

Subscribe to this mod's changes

daily-planner-propose is a skill published in the GitHub repository businessbarista/daily-planner-skill (52 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 684 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens