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/sageox/ox/feature-designgit clone --depth 1 https://github.com/sageox/oxWhat 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 | $0.00099 | $0.00887 |
| Opus 5 | $0.00049 | $0.00443 |
| Sonnet 5 | $0.00020 | $0.00177 |
| Haiku 4.5 | $0.00010 | $0.00089 |
Grade A, and why
feature-design 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Design
A skill for structured feature elicitation: ask the right questions to surface goals, constraints, and tradeoffs, then produce a concise design brief.
Phase 1 — Orientation (1–2 questions max)
Start with a single open question to get the user talking:
"What problem does this feature solve, and who runs into it?"
Let them answer freely. Extract from their response:
- Actor: who is affected (user, operator, agent, system)
- Trigger: what situation or pain prompts the need
- Outcome: what changes if this works well
If either actor or outcome is still unclear after their first answer, ask one targeted follow-up. Don't ask more than two questions in Phase 1.
Phase 2 — Structured Elicitation
Once you have basic orientation, work through the following dimensions. Don't ask all at once — cluster 2–3 related questions per turn, adapt based on what the user has already said, and skip anything already answered.
Goals & Success
- What does success look like? How would you know it's working?
- Is there a metric, behavior change, or user outcome you're optimizing for?
- Are there anti-goals — things this feature explicitly should not do?
Users & Context
- Who uses this, and how often? (power users vs. occasional; human vs. agent)
- What's the context of use — what are they doing right before and after?
- Are there distinct user segments with different needs?
Constraints & Scope
- What's the delivery pressure — prototype, MVP, or production-grade?
- Are there technical, regulatory, or resource constraints to design around?
- What's explicitly out of scope for now?
Tradeoffs & Risks
- What's the biggest thing that could go wrong?
- Are there competing approaches you're already considering?
- What would you sacrifice to ship faster?
Dependencies & Fit
- Does this touch existing systems, APIs, or data flows?
- Are there other features or teams this needs to coordinate with?
- Is there prior art — internal or external — worth learning from?
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 · 108 lines · 99 tokens per session scan A 74de158377d6
feature-design is a command published in the GitHub repository sageox/ox (50 stars, last pushed 4d ago), licensed MIT. It adds 99 tokens to every session and 887 once invoked, about $0.0005 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
om-vault-audit
Deep structural audit of the vault. Checks indexes, folder placement, frontmatter, links, Bases, and consistency. Fix what can be fixed, flag what needs user input.
om-incident-capture
Capture an incident from Slack channels, DMs, and threads into structured vault notes. Produces a complete incident work note with timeline, people, analysis, and brag doc entry.
om-intake
Process all unread meeting notes in work/meetings/ — reads each file, classifies content, routes to the right vault notes, then clears the inbox.
om-wrap-up
Full session review before ending. Review context, ways of working, files modified, consistency, and suggest improvements.
om-meeting
Prep for any meeting by topic — subject-forward briefing with open tasks, blockers, and brainstormed considerations the user may not have thought of yet.
om-capture-1on1
Take a meeting transcript, notes, or Gemini summary and create a structured vault note with key takeaways, quotes, action items, and DM context.