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/shyftai/gtmos/todaygit clone --depth 1 https://github.com/shyftai/GTMOSWrote 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/shyftai/gtmos/today)<a href="https://agentmods.dev/commands/shyftai/gtmos/today"><img src="https://agentmods.dev/badge/commands/shyftai/gtmos/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 | $0.01054 |
| Opus 5 | $0.00008 | $0.00527 |
| Sonnet 5 | $0.00003 | $0.00211 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
gtm: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 5d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 5d ago First seen · 98 lines · 16 tokens per session scan A a0320ed3a645
gtm:today is a command published in the GitHub repository shyftai/GTMOS (42 stars, last pushed 2mo ago), with no licence file. It adds 16 tokens to every session and 1,054 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
why-change
Create a Why Change sales pitch for a named customer or market segment.
capture-meeting
Capture a meeting or inbound touch from a named person. Say "capture this", "log this", "I had a call with ", "I spoke to ", "I got a reply from ", "heard back from ", "they replied", or " responded" (or run /capture-meeting ). Routes a transcript or brain dump into brain/log.md + context/clients.md + open…
strategic-read
Produce a state-of-the-OS report from the current file layer. Say "give me a strategic read", "where am I", or run /founder-os:strategic-read. Returns 5 sections by default; pass a section key (identity, commitments, decisions, flags, next-moves) to render only that section. Read-only.
capture-sweep
Notice what was recorded and propose where it goes. Say "sweep my meetings", "anything new to capture", or run /founder-os:capture-sweep. Sorts each item (client conversation, training media, internal, personal) and proposes queue items plus provisional-fact rows. Propose only - it never files a record or does the…
employee-review
Review one recurring job the OS runs for you and propose changes to it. Say "review the follow-up watcher" or run /founder-os:employee-review . Reads its row, its verdicts, and what it filed, then proposes a shown diff. Never applies its own diff.
os-evolve
Plan the next round of OS improvements. Say "evolve the OS" or run /founder-os:os-evolve [path to an audit or plan]. Scores the last cycle, writes gaps with evidence and numbered execute prompts into one dated plan file. Plans only - never executes its own prompts.