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 agentmods add commands/conorbronsdon/agent-context-os/todaygit clone --depth 1 https://github.com/conorbronsdon/agent-context-osWrote 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/commands/conorbronsdon/agent-context-os/today)<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>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 | $0.00016 | $0.01217 |
| Opus 5 | $0.00008 | $0.00609 |
| Sonnet 5 | $0.00003 | $0.00243 |
| Haiku 4.5 | $0.00002 | $0.00122 |
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.
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 thanstaleness.current_days→ flagweekly-priorities.md**Week of:**from a previous week (or older thanstaleness.weekly_days) → flagblockers.mdolder thanstaleness.blockers_days→ flag- Open threads in
current.mdcarrying 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.
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 First seen · 121 lines · 16 tokens per session scan A f1446573aa34
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.
Other commands, from other repositories
recall-loop
Periodic memory digest — designed for use with Claude Code's /loop scheduler. Shows recent memories and pending to-dos in a compact, scannable format.
context-stats
Show context window usage, active tier, and system stats.
save
Save a Wingman handoff for the next tool or machine.
digest
What happened in a given week, verbatim.
timeline
Chronological history of this project's sessions, grouped by week.
handoff
Write a session handoff file for the current session.