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 skills/otto-haus/otto/routinenpx 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.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 | $0.00051 | $0.00826 |
| Opus 5 | $0.00026 | $0.00413 |
| Sonnet 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 4d 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.
- 4d 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 3d ago), licensed MIT. It adds 51 tokens to every session and 826 once invoked, about $0.0003 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 skills, from other repositories
check-work
Check your work with a verification subagent that reviews diffs, runs builds and tests, and evaluates correctness. Read this file for instructions. Use when asked to "check work", "verify changes", "self-verify", "/check-work", "/check", "/verify", or "/self-verify".
create-skill
Interactively create a new Grok skill (SKILL.md + optional scripts/references). Use when the user wants to create a skill, scaffold a skill, or runs /create-skill.
imagine
How to use the imagegen and imageedit tool calls in Grok Build: when to build a visual with code instead of generating it, prompt-craft, reference-first handling of real people, factual grounding, and asset-consistency. Load this whenever generating or editing an image is on the table, i.e. when an imagegen or…
best-of-n
Implement a task N ways in parallel and pick the best. Spawns multiple subagents in isolated worktrees, evaluates all candidates, and applies the winner. Use when asked to "best of n", "try multiple approaches", "parallel implementations", "/best-of-n", or "/bon".
help
Grok documentation and configuration help. Use when users ask about setup, configuration, MCP servers, authentication, skills, slash commands, keyboard shortcuts, or any Grok feature. Also use proactively when you detect a user is having trouble with setup or onboarding.
safety-guardrails
Flags risky shell commands and unsafe tree ops.