traverse CLAUDE.md

A development guide for Traverse, a software framework with a Rust core and host integrations for languages such as TypeScript, Swift, Kotlin, and .NET. It describes the project's rules, technologies, folders, and current scope.

In plain words
What is it for?
Navigating the Traverse codebase and planning or implementing changes across its Rust workspace, runtime, contracts, registry, and host integrations.
Why use it?
It points coding agents to the governing documents and the parts of the repository they should understand before making changes. This helps keep work aligned with the project's compatibility and architecture rules.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/traverse-framework/traverse/claude-md
Clone the repo
git clone --depth 1 https://github.com/traverse-framework/traverse
Per session 670 This file is loaded in full into every session.
When invoked 670 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00670 $0.00670
Opus 5 $0.00335 $0.00335
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured 2d ago against content hash 7d55f61280c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

traverse CLAUDE.md 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.

CLAUDE.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Traverse Development Guidelines

Auto-generated. Last updated: 2026-07-28

Governance

This repo's constitution, NFRs, quality standards, antipatterns, compatibility policy, exception process, and CLA are not duplicated here — they live in traverse-framework/.github, pinned at the version recorded in .governance-version. Read that repo's constitution.md before any implementation work.

Repo-specific product scope stays here: see specs/001-foundation-v0-1/spec.md for this repo's v0.1 scope, and specs/051-registry-extraction/spec.md for the in-progress registry extraction.

Active Technologies

  • Rust 1.94+; host packages in TypeScript, Swift, Kotlin, and .NET + Cargo workspace, serde, semver, existing registry and embedder packages (524-production-app-readiness)

  • host-owned verified artifact cache, append-only trace journal, host-owned file-backed DataStore v2 (524-production-app-readiness)

  • Rust 1.94+

  • Cargo workspace

  • serde (JSON serialization)

  • semver

  • WASM (target)

Project Structure

crates/
  traverse-runtime/      # Core execution engine
  traverse-contracts/    # Contract definitions and validation
  traverse-cli/          # Command-line interface
  traverse-mcp/          # Model Context Protocol (stub)
specs/                   # Versioned, immutable governing specs
contracts/               # Capability and event contracts
docs/                    # Repo-specific docs (shared governance docs live in traverse-framework/.github)
.specify/                # Speckit: scripts, templates (constitution lives in traverse-framework/.github)
scripts/ci/              # Deterministic spec-alignment gate (vendored, pinned copy of traverse-framework/.github's version)

Commands

cargo build              # Build all crates
cargo test               # Run tests (no panics, unwraps, or TODOs)
cargo run -p traverse-cli-rs
bash scripts/ci/spec_alignment_check.sh   # Spec-alignment gate

Read the full file on GitHub · 75 lines

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.

  1. 2d ago First seen · 75 lines · 670 tokens per session scan A 7d55f61280c0

Subscribe to this mod's changes

traverse CLAUDE.md is an instructions file published in the GitHub repository traverse-framework/traverse (93 stars, last pushed 2d ago), licensed Apache-2.0. It adds 670 tokens to every session, about $0.0034 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.