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 OutlineDriven/odin-gemini-cli-extension --skill duetgit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/duet)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/duet"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/duet.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 5.1 | $0.00073 | $0.03533 |
| Opus 5 | $0.00036 | $0.01767 |
| Sonnet 5 | $0.00015 | $0.00707 |
| Haiku 4.5 | $0.00007 | $0.00353 |
Grade A, and why
duet 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 8d 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.
This is a copy
89% identical to duet — 111 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Duet
Two-party working posture: user is the director, agent is the executor.
Why this exists
Working with agents has two chronic failure modes:
- Review bottleneck — the agent does everything, the user becomes a reviewer of a giant diff at the end. Review is slow, exhausting, and frequently misses things the user would have caught at the moment of the choice.
- Codebase-understanding debt — when the agent silently picks architecture, libraries, boundaries, and names on the user's behalf, the user ends up owning code they do not understand. The debt compounds: every future change requires the user to re-learn what the agent decided for them.
Duet addresses both by doing one simple thing: surface every genuine fork as a pick, in plain structural language, at the moment of the decision. Review gets distributed across the task — there is no giant diff at the end because every call was already consented to. And because the user picked, the user remembers — the mental model is built as the code is built, not reconstructed afterward.
This is the load-bearing principle. Everything below is mechanics.
Role inversion
- Agent → executor. Carries the jargon, the tooling, the syntax, the plumbing, the reading of unfamiliar code. Translates a technical surface into a small set of human-picksable options.
- User → director. Makes every call on scope, boundaries, taste, naming-that-will-be-read-often, architecture, and anything irreversible.
The agent's value-add is compression: turning a technical surface the user doesn't want to carry into a decision the user does want to carry.
Antipatterns and shape discipline [LOAD-BEARING]
Never use multiSelect for axis-with-default override semantics. The "rarely has to type" objective is satisfied by N per-axis single-select questions with (Recommended) first — never by collapsing N axes into one multi-pick checklist.
VS-gated question protocol [MANDATORY]
Run VS + falsifier protocol before every AskUserQuestion fire (Phase 1, Phase 2, Phase 3). Duet-specific deltas only — askme owns the canonical spec:
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.
- 8d ago First seen · 214 lines · 73 tokens per session scan A 169fa2021281
duet is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 3,533 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to duet, differing in 111 lines, and is treated as a copy.
Other skills, from other repositories
tidy
Tidy-operations dispatcher. Invoke on "tidy", "clean up", "tidy this file/memory/workspace/git/docs", or when active context (current file, diff, stack, memory directory) has structural rot to resolve before touching behavior. Detects target domain from context and routes to the sibling skill. Requires explicit target…
proceed
Execute an implementation plan with surgical precision. Use after a planning phase (plan-now or similar) has produced a step-by-step strategy and identified critical files. Focuses on precise code changes with verification at each step.
ai-collab-protocols
Surface in-task-collaboration protocols when the user describes an AI workflow informally — URL-as-entity-reference, PR-comment threads as session memory. Trigger when the user names entities by colloquial label instead of stable URL, asks "how should I structure this for Claude", or describes a multi-step Claude…
inbox
Drain parked decisions — read a tagged digest of every blockedonquestion task's open questions, pick which to answer now, deep-dive each via AskUserQuestion, and record the answer through the answer verb. One pass, suggest-don't-force, no self-loop.
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…