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 skills add otto-haus/otto --skill routinegit clone --depth 1 https://github.com/otto-haus/ottoWrote 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/skills/otto-haus/otto/routine)<a href="https://agentmods.dev/skills/otto-haus/otto/routine"><img src="https://agentmods.dev/badge/skills/otto-haus/otto/routine/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.
<a href="https://agentmods.dev/skills/otto-haus/otto/routine"><img src="https://agentmods.dev/badge/skills/otto-haus/otto/routine.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00051 | $0.00826 |
| Opus 5.5 | $0.00020 | $0.00330 |
| Sonnet 5.5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
routine 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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routine
A Routine is a repeated bundle of canonical Practices.
Practices make culture executable.
Routines make Practices compound.
Receipts prove behavior changed.
Core rule
Routine proposal can be autonomous.
One-off low-risk trial can be autonomous.
Recurring activation belongs to the human. <- attention is a one-way door
Permissions / effects belong to the human.
Do not enable a recurring schedule without human approval, even if no new tool permission is needed.
Contract
Routine specs conform to Routine in packages/core/src/types.ts:
id,slug,name,status,summary,steps[],attention_cost,requires_approval_to_activate,created_at- optional
schedulewithcronorrrule, plustimezone steps[].practicemust be one of:charter,decision,review,field-note,follow-up- any recurring/standing Routine sets
requires_approval_to_activate: true
Runtime
Default root: $ROUTINE_HOME/, else $OTTO_HOME/ (or $VINNY_HOME/ for back-compat), falling back to ~/.otto.
routines/<slug>/routine.yaml product truth
runs/ runtime execution records (gitignored)
receipts/ proof artifacts / quick-audit surface (gitignored)
Files = truth. Memory = lessons. UI = workspace.
Subcommands
list
List Routines with status, schedule, attention cost, approval requirement, last Run, and obvious blocks. Flag recurring Routines that lack activation approval.
show
Render the Routine spec and recent Runs/Receipts. Verify each step references a canonical Practice slug.
run
Execute one on-demand trial only. Do not schedule anything. Run the Practice steps in order, honor every Practice gate, label missing data, and produce a Run record plus a Receipt or a block.
pause
Set status: paused and disable the backend schedule. Pausing is reversible.
resume
Recurring activation. Show the spec and attention cost, then ask exactly:
Activate '<slug>' on its recurring schedule? (approve / trial-once / cancel).
Only on approval may you set status: active and register the schedule.
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.
- 1mo ago First seen · 106 lines · 51 tokens per session scan A 23541618b844
routine is a skill published in the GitHub repository otto-haus/otto (7 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 826 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
slack
Use when you need to control Slack from Brigade via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
scheduling-tasks
Advanced scheduling through the letta cron CLI for other conversations, computers, run history, and schedule replacement. Use Wake for ordinary create/list/cancel operations in the current conversation.
dws
A command-line guide for DingTalk, a workplace platform with chat, documents, calendars, approvals, tasks, and other business tools.
subscription-setup
A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history, or import a local recording. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.