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/arcassystems/founderos/todaygit clone --depth 1 https://github.com/ARCASSystems/FounderOSWhat 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 | $0.00043 | $0.00853 |
| Opus 5 | $0.00022 | $0.00426 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00085 |
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 2d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Today
One-screen view of what matters today. No scrolling. No prose. Read-only.
Procedure (in order)
-
Read
cadence/daily-anchors.md. Extract the## Today:section: anchor line + top 3 tasks. -
Read
context/decisions.md. Extract the top 3 Pending decisions by deadline proximity. -
Read
brain/flags.md. Extract active flags. Top 3. -
Read
brain/log.md. Extract the first line of the last 3 entries (newest on top). -
If a calendar MCP is available (Google Calendar, Outlook), fetch the next scheduled event within the next 24 hours. Otherwise skip that line.
-
Render the output as a single fenced block, exactly this structure. No commentary before, after, or around it.
TODAY - <YYYY-MM-DD> Anchor: <anchor line from daily-anchors> OPEN DECISIONS (top 3 by deadline) - <title> - <deadline> - <title> - <deadline> - <title> - <deadline> ACTIVE FLAGS - <flag name> - <flag name> - <flag name> LAST 3 SESSIONS - <first line of session entry 1> - <first line of session entry 2> - <first line of session entry 3> NEXT: <calendar event title at HH:MM> | <"no scheduled event next 24h"> -
If a section has nothing, write the header and one line:
none open.Do not skip the section. -
Day-one exception: if the anchor is
[NOT SET]and the log holds one entry or fewer, do NOT render the fenced block. Reply instead, outside any block:Nothing on today yet - that is normal on day one. Tell me the one thing you have to get done and I will make it today's anchor.Placeholders rendered as a dashboard read as broken; a question reads as a start.
What counts as progress here
Two behavior rules on what this brief reports. They change what the founder sees on a busy day, so they are not stylistic.
Read back what moved, not what got closed. The LAST 3 SESSIONS lines name outcomes: a reply that came in, a decision that got made, a thing that shipped, a payment that landed. Not "three items closed". Closing items is motion, and motion is easy to generate and easy to mistake for progress. If a day genuinely moved nothing, the honest line is that nothing moved. A brief that always looks productive is a brief nobody believes by the second week.
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.
- 2d ago First seen · 65 lines · 0 tokens per session scan A 56634500e403
today is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 18d ago), licensed MIT. It adds 43 tokens to every session and 853 once invoked, about $0.0002 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 commands, from other repositories
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.
wiki-digest
Generate a daily or weekly digest of wiki changes — new sources, pages, insights, and gaps.
demo-command
Example slash command that wraps the demo-skill. Showcases the command kind.
ingest-l1
L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…
web-search
Search fetched web-source Markdown by regex and pull surrounding context for the best hits. Optionally restrict to one source alias.
docs-refresh
Re-fetch a cached source, ignoring the 7-day cache. Use when upstream content has changed.