Files
skills/public/agent-design.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

256 lines
22 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>agent-design</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/agent-design.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/agent-design">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/agent-design.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>agent-design</h1><p class="lede">This file covers decision heuristics for building agents on the Claude API: which primitives to reach for, how to design your tool surface, and how to manage context and cost over long runs.</p><h1>Agent Design Patterns</h1>
<p>This file covers decision heuristics for building agents on the Claude API: which primitives to reach for, how to design your tool surface, and how to manage context and cost over long runs. For per-tool mechanics and code examples, see <code>tool-use-concepts.md</code> and the language-specific folders.</p>
<hr>
<h2>Model Parameters</h2>
<p>| Parameter | When to use it | What to expect | | --- | --- | --- | | <strong>Adaptive thinking</strong> (<code>thinking: {type: &quot;adaptive&quot;}</code>) | When you want Claude to control when and how much to think. | Claude determines thinking depth per request and automatically interleaves thinking between tool calls. No token budget to tune. | | <strong>Effort</strong> (<code>output_config: {effort: ...}</code>) | When adjusting the tradeoff between thoroughness and token efficiency. | Lower effort → fewer and more-consolidated tool calls, less preamble, terser confirmations. <code>medium</code> is often a favorable balance. Use <code>max</code> when correctness matters more than cost. |</p>
<p>See <code>SKILL.md</code> §Thinking &amp; Effort for model support and parameter details.</p>
<hr>
<h2>Designing Your Tool Surface</h2>
<h3>Bash vs. dedicated tools</h3>
<p>Claude doesn&#x27;t know your application&#x27;s security boundary, approval policy, or UX surface. Claude emits tool calls; your harness handles them. The shape of those tool calls determines what the harness can do.</p>
<p>A <strong>bash tool</strong> gives Claude broad programmatic leverage — it can perform almost any action. But it gives the harness only an opaque command string, the same shape for every action. Promoting an action to a <strong>dedicated tool</strong> gives the harness an action-specific hook with typed arguments it can intercept, gate, render, or audit.</p>
<p><strong>When to promote an action to a dedicated tool:</strong></p>
<ul><li><strong>Security boundary.</strong> Actions that require gating are natural candidates. Reversibility is a useful criterion: hard-to-reverse actions (external API calls, sending messages, deleting data) can be gated behind user confirmation. A <code>send_email</code> tool is easy to gate; <code>bash -c &quot;curl -X POST ...&quot;</code> is not.</li><li><strong>Staleness checks.</strong> A dedicated <code>edit</code> tool can reject writes if the file changed since Claude last read it. Bash can&#x27;t enforce that invariant.</li><li><strong>Rendering.</strong> Some actions benefit from custom UI. Claude Code promotes question-asking to a tool so it can render as a modal, present options, and block the agent loop until answered.</li><li><strong>Scheduling.</strong> Read-only tools like <code>glob</code> and <code>grep</code> can be marked parallel-safe. When the same actions run through bash, the harness can&#x27;t tell a parallel-safe <code>grep</code> from a parallel-unsafe <code>git push</code>, so it must serialize.</li></ul>
<p><strong>Rule of thumb:</strong> Start with bash for breadth. Promote to dedicated tools when you need to gate, render, audit, or parallelize the action.</p>
<hr>
<h2>Anthropic-Provided Tools</h2>
<p>| Tool | Side | When to use it | What to expect | | --- | --- | --- | --- | | <strong>Bash</strong> | Client | Claude needs to execute shell commands. | Claude emits commands; your harness executes them. Reference implementation provided. | | <strong>Text editor</strong> | Client | Claude needs to read or edit files. | Claude views, creates, and edits files via your implementation. Reference implementation provided. | | <strong>Computer use</strong> | Client or Server | Claude needs to interact with GUIs, web apps, or visual interfaces. | Claude takes screenshots and issues mouse/keyboard commands. Can be self-hosted (you run the environment) or Anthropic-hosted. | | <strong>Code execution</strong> | Server | Claude needs to run code in a sandbox you don&#x27;t want to manage. | Anthropic-hosted container with built-in file and bash sub-tools. No client-side execution. | | <strong>Web search / fetch</strong> | Server | Claude needs information past its training cutoff (news, current events, recent docs) or the content of a specific URL. | Claude issues a query or URL; Anthropic executes it and returns results with citations. | | <strong>Memory</strong> | Client | Claude needs to save context across sessions. | Claude reads/writes a <code>/memories</code> directory. You implement the storage backend. |</p>
<p><strong>Client-side</strong> tools are defined by Anthropic (name, schema, Claude&#x27;s usage pattern) but executed by your harness. Anthropic provides reference implementations. <strong>Server-side</strong> tools run entirely on Anthropic infrastructure — declare them in <code>tools</code> and Claude handles the rest.</p>
<hr>
<h2>Composing Tool Calls: Programmatic Tool Calling</h2>
<p>With standard tool use, each tool call is a round trip: Claude calls the tool, the result lands in Claude&#x27;s context, Claude reasons about it, then calls the next tool. Three sequential actions (read profile → look up orders → check inventory) means three round trips. Each adds latency and tokens, and most of the intermediate data is never needed again.</p>
<p><strong>Programmatic tool calling (PTC)</strong> lets Claude compose those calls into a script instead. The script runs in the code execution container. When the script calls a tool, the container pauses, the call is executed (client-side or server-side), and the result returns to the running code — not to Claude&#x27;s context. The script processes it with normal control flow (loops, filters, branches). Only the script&#x27;s final output returns to Claude.</p>
<p>| When to use it | What to expect | | --- | --- | | Many sequential tool calls, or large intermediate results you want filtered before they hit the context window. | Claude writes code that invokes tools as functions. Runs in the code execution container. Token cost scales with final output, not intermediate results. |</p>
<hr>
<h2>Scaling the Tool and Instruction Set</h2>
<p>| Feature | When to use it | What to expect | | --- | --- | --- | | <strong>Tool search</strong> | Many tools available, but only a few relevant per request. Don&#x27;t want all schemas in context upfront. | Claude searches the tool set and loads only relevant schemas. Tool definitions are appended, not swapped — preserves cache (see Caching below). | | <strong>Skills</strong> | Task-specific instructions Claude should load only when relevant. | Each skill is a folder with a <code>SKILL.md</code>. The skill&#x27;s description sits in context by default; Claude reads the full file when the task calls for it. |</p>
<p>Both patterns keep the fixed context small and load detail on demand.</p>
<hr>
<h2>Long-Running Agents: Managing Context</h2>
<p>| Pattern | When to use it | What to expect | | --- | --- | --- | | <strong>Context editing</strong> | Context grows stale over many turns (old tool results, completed thinking). | Tool results and thinking blocks are cleared based on configurable thresholds. Keeps the transcript lean without summarizing. | | <strong>Compaction</strong> | Conversation likely to reach or exceed the context window limit. | Earlier context is summarized into a compaction block server-side. See <code>SKILL.md</code> §Compaction for the critical <code>response.content</code> handling. | | <strong>Memory</strong> | State must persist across sessions (not just within one conversation). | Claude reads/writes files in a memory directory. Survives process restarts. |</p>
<p><strong>Choosing between them:</strong> Context editing and compaction operate within a session — editing prunes stale turns, compaction summarizes when you&#x27;re near the limit. Memory is for cross-session persistence. Many long-running agents use all three.</p>
<hr>
<h2>Caching for Agents</h2>
<p><strong>Read <code>prompt-caching.md</code> first.</strong> It covers the prefix-match invariant, breakpoint placement, the silent-invalidator audit, and why changing tools or models mid-session breaks the cache. This section covers only the agent-specific workarounds for those constraints.</p>
<p>| Constraint (from <code>prompt-caching.md</code>) | Agent-specific workaround | | --- | --- | | Editing the system prompt mid-session invalidates the cache. | Append a <code>{&quot;role&quot;: &quot;system&quot;, ...}</code> message to <code>messages[]</code> instead (no beta header; on supporting models — see <code>prompt-caching.md</code> § Mid-conversation system messages). The cached prefix stays intact, and the model treats it as an operator-authority instruction rather than user text. On models that don&#x27;t support it, fall back to a <code>&lt;system-reminder&gt;</code> text block in the user turn. | | Switching models mid-session invalidates the cache. | Spawn a <strong>subagent</strong> with the cheaper model for the sub-task; keep the main loop on one model. On Managed Agents that is a <code>multiagent</code> roster entry — see <code>managed-agents-multiagent.md</code>. | | Adding/removing tools mid-session invalidates the cache. | Use <strong>tool search</strong> for dynamic discovery — it appends tool schemas rather than swapping them, so the existing prefix is preserved. |</p>
<p>For multi-turn breakpoint placement, use top-level auto-caching — see <code>prompt-caching.md</code> §Placement patterns.</p>
<hr>
<p>For live documentation on any of these features, see <code>live-sources.md</code>.</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/agent-design.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>