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 tslateman/duet --skill iagit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/ia)<a href="https://agentmods.dev/skills/tslateman/duet/ia"><img src="https://agentmods.dev/badge/skills/tslateman/duet/ia/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/tslateman/duet/ia"><img src="https://agentmods.dev/badge/skills/tslateman/duet/ia.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 | $0.00054 | $0.02128 |
| Opus 5.5 | $0.00022 | $0.00851 |
| Sonnet 5.5 | $0.00011 | $0.00426 |
| Haiku 4.5 | $0.00005 | $0.00213 |
Grade A, and why
ia 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Information Architecture
Overview
Information architecture is the structural design of shared information environments. When someone asks "where does this go?" or "I can't find anything", that's an IA problem.
Grounded in Rosenfeld, Morville & Arango's Information Architecture (4th ed.) and the Diataxis documentation framework. See references/rosenfeld-morville.md for the core systems and references/organizing-principles.md for LATCH, Brown's eight principles, and Morville's triad.
Three layers, before the systems. Morville separates an information space into ontology (what the entities mean and how they relate), taxonomy (how they are grouped), and choreography (how the space behaves as people move through it over time). Most IA effort lands on taxonomy. When a space audits clean structurally and still feels wrong, the defect sits in one of the other two: confusion about what things mean is ontology, confusion about what to do next is choreography.
The Four Systems
Every information space has four structural systems; evaluate each when reviewing or designing. references/rosenfeld-morville.md carries the full treatment (schemes, structures, label types, navigation modes, search components); this is the working summary.
- Organization: how content is grouped. Choose one primary scheme per level (exact: alphabetical, chronological, geographic; ambiguous: by topic, task, audience). Mixing schemes at one level confuses navigation.
- Labeling: what things are called. Describe content, not container ("Authentication", not "Section 3"); match the words users search for; introduce jargon inside, not at top levels.
- Navigation: how people move. Global (always visible), local (within a section), contextual (inline links), supplemental (index, site map, search). Three clicks to any content, or flatten the hierarchy.
- Search: how people find without browsing. Grep-friendly file names (
signal-contract.md, notdoc-7.md), headings that match search terms, synonym cross-references, consistent metadata.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +41 lines 0eaece525acf
- 1mo ago First seen · 142 lines · 54 tokens per session scan A 01519e033e09
ia is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 2,128 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
skill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery.
release-notes
Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.
recipe-front-adjust
Adjust an already-implemented UI in-session with verification against the design source.
recipe-front-design
Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
git-workflow
Manages branches, worktrees, atomic commits, and branch completion by merge, PR, preserve, or discard. Use when starting feature work that needs a branch or an isolated workspace, making commits during development, or finishing a development branch. Also use when the user says "set up worktree", "create PR", "finish…