today

today is a command for Claude Code from conorbronsdon/agent-context-os. It costs 16 tokens per session (1,217 once invoked), scanned A, original, MIT.

A user-invoked morning check that reviews repository activity, detects stale work, surfaces deadlines and blockers, and updates a local heartbeat log.

In plain words
What is it for?
Use it for a daily workspace check based on recent Git history, saved state, session records, task files, and documented staleness thresholds.
Why use it?
It catches changes and unfinished work from recent days, including sessions that ended without a formal close command.

Command for Claude Code

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.

agentmods
npx agentmods add commands/conorbronsdon/agent-context-os/today
Clone the repo
git clone --depth 1 https://github.com/conorbronsdon/agent-context-os

Made for: Claude Code.

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.

agentmods badge for today

README.md
[![agentmods](https://agentmods.dev/badge/commands/conorbronsdon/agent-context-os/today.svg)](https://agentmods.dev/commands/conorbronsdon/agent-context-os/today)
Your own site
<a href="https://agentmods.dev/commands/conorbronsdon/agent-context-os/today"><img src="https://agentmods.dev/badge/commands/conorbronsdon/agent-context-os/today.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,217 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01217
Opus 5 $0.00008 $0.00609
Sonnet 5 $0.00003 $0.00243
Haiku 4.5 $0.00002 $0.00122

Measured 3d ago against content hash f1446573aa34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

today 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.

.claude/commands/today.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/today — Morning Heartbeat

Lightweight daily check-in that catches staleness, surfaces deadlines, and proposes state updates — including gaps left by sessions that closed without /end. Run at the start of each day or after any long gap between sessions. Designed to finish in under 60 seconds — if it's slow, it won't get used.

Invocation: user-timed and explicitly user-invoked. The heartbeat writes its audit log, so it is not an ambient read-only helper.

Configuration

Run bash scripts/contextos.sh workspace show and use its resolved <state_dir>, <sessions_dir>, and <task_file>. Canonical JSON is authoritative; legacy YAML is used only when JSON is absent. Stop and report a configuration error instead of guessing paths. Schema v1 does not store staleness policy, so use the documented defaults: current 3 days, weekly 5 days, blockers 7 days.

Instructions

1. Establish context

Run date +%Y-%m-%d and date +%A. Read <state_dir>/heartbeat-log.md (if present) to find the last check-in date.

2. Scan recent activity

Catch work even from sessions that closed without /end. In a git repository:

git log --oneline --since="3 days ago"

Also check <sessions_dir> for logs newer than the last heartbeat. Note what was last worked on for continuity. Outside a git repository, rely on the session logs alone.

3. Load state

Read <state_dir>/current.md, <state_dir>/weekly-priorities.md, and <state_dir>/blockers.md.

4. Check staleness (escalating)

  • current.md **Last Updated:** older than staleness.current_days → flag
  • weekly-priorities.md **Week of:** from a previous week (or older than staleness.weekly_days) → flag
  • blockers.md older than staleness.blockers_days → flag
  • Open threads in current.md carrying a date annotation:
    • older than 7 days → "stale — still relevant?"
    • older than 14 days → "likely stale — remove or convert to a task?"

Present these as proposals. Do not auto-update.

Read the full file on GitHub · 121 lines

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.

  1. 3d ago First seen · 121 lines · 16 tokens per session scan A f1446573aa34

Subscribe to this mod's changes

today is a command published in the GitHub repository conorbronsdon/agent-context-os (17 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 1,217 once invoked, about $0.0001 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.