What is traverse-app-builder?

A plan-first workflow for building apps with Traverse by combining reusable capabilities into a reviewed workflow. Each capability declares its inputs, outputs, required conditions, and permissions, and the final workflow is sealed before it runs.

Use it to discover available capabilities, plan an app, add atomic capabilities when needed, obtain explicit confirmation, and write the final workflow definition.

It prevents an app from changing its workflow unexpectedly at runtime and makes the planned operations and permissions reviewable. It also provides a process for creating missing capabilities when the registry has no suitable one.

How traverse-framework/traverse configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to traverse-framework/traverse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/traverse-framework/traverse/main/.agents/skills/traverse-app-builder/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/traverse-framework/traverse

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/traverse-framework/traverse/traverse-app-builder/github.svg)](https://agentmods.dev/skills/traverse-framework/traverse/traverse-app-builder)

Your own site

<a href="https://agentmods.dev/skills/traverse-framework/traverse/traverse-app-builder"><img src="https://agentmods.dev/badge/skills/traverse-framework/traverse/traverse-app-builder/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/traverse-framework/traverse/traverse-app-builder"><img src="https://agentmods.dev/badge/skills/traverse-framework/traverse/traverse-app-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,471 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00127	$0.02471
Opus 5.5	$0.00051	$0.00988
Sonnet 5.5	$0.00025	$0.00494
Haiku 4.5	$0.00013	$0.00247

Measured 1mo ago against content hash cbc317e54d92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

traverse-app-builder 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.

.agents/skills/traverse-app-builder/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building apps with Traverse (Decision 80)

Traverse's differentiator is contracts: every capability declares JSON-Schema inputs/outputs, preconditions, postconditions, and permissions, and the runtime enforces them. An app is usually reused registry capabilities + a few new atomic ones + a sealed workflow that chains them.

Product default (Decision 80): plan at authoring time, then seal. What ships and runs is a reviewed, pinned workflow.json referenced from the app/package manifest (known_compositions). Runtime adaptive composition is explicit opt-in only (see #1345) — never the default, and never silently persisted as the app's sealed workflow.

Thin product pointer in-repo: docs/workflow-authoring-guide.md. This skill is the canonical deep ritual.

Before you start

Rust + wasm32-unknown-unknown (rustup target add wasm32-unknown-unknown). Not wasm32-wasip1 for guest capabilities — see the ABI section below.
A clone of traverse-framework/traverse for traverse-cli and examples.

Homebrew/rustup PATH trap: if both are installed, which rustc may point at Homebrew and wasm32-unknown-unknown builds fail with missing core. Fix with PATH="$(dirname "$(rustup which cargo)"):$PATH" — do not invent toolchain paths from uname -m (arm64 ≠ rustup's aarch64-apple-darwin).

Decision 80 ritual (primary path)

Do this every authoring session unless the user already has a sealed graph and only needs a validation/repair pass.

1. Clarify the goal

Capture a structured target: desired outcome facts / capability chain intent, inputs available at start, and any hard constraints (targets, permissions).

2. Discover what already exists

traverse-cli registry sync --workspace <workspace-id> --json
# then read .traverse/workspaces/<workspace-id>/registry/public/index.json

The public index is a thin pointer (id, version, digests, URLs) — fetch contract_url before deciding a candidate fits. For capabilities already in a bundle: traverse-cli capability discover <bundle-manifest> --json. Details: references/registry.md.

Read the full file on GitHub · 245 lines

Files

What ships with it

5 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.

Changes

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 First seen · 245 lines · 127 tokens per session scan A cbc317e54d92

Subscribe to this mod's changes

traverse-app-builder is a skill published in the GitHub repository traverse-framework/traverse (89 stars, last pushed 6d ago), licensed Apache-2.0. It adds 127 tokens to every session and 2,471 once invoked, about $0.0005 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 2026-09-12.

Building agents Planning business-logic capabilities cli contracts event-driven mcp

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

interview

Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.

Hmbown/CodeWhale · 40 tokens

refocusing

Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.

mvschwarz/openrig · 59 tokens

traverse: Skill for Claude Code