What is voyager-agent?

A general planning and routing skill for developing with the Axelera AI Voyager SDK on Metis hardware. It helps identify the task, hardware, environment, and more specific Voyager workflows to use.

Use it to plan pipeline, deployment, inference, benchmarking, or debugging work, and to route focused tasks such as launching, creating, running, or deploying a pipeline.

It gives broad repository orientation when a request spans several areas or does not fit one focused workflow.

voyager-agent — Skill for Claude Code by fxd0h

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.

Any agent

npx skills add fxd0h/Axelera-Voyager-Local-Assistant --skill voyager-agent

Clone the repo

git clone --depth 1 https://github.com/fxd0h/Axelera-Voyager-Local-Assistant

Made for: Claude Code.

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/fxd0h/axelera-voyager-local-assistant/voyager-agent/github.svg)](https://agentmods.dev/skills/fxd0h/axelera-voyager-local-assistant/voyager-agent)

Your own site

<a href="https://agentmods.dev/skills/fxd0h/axelera-voyager-local-assistant/voyager-agent"><img src="https://agentmods.dev/badge/skills/fxd0h/axelera-voyager-local-assistant/voyager-agent/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/fxd0h/axelera-voyager-local-assistant/voyager-agent"><img src="https://agentmods.dev/badge/skills/fxd0h/axelera-voyager-local-assistant/voyager-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 447 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	$0.00095	$0.00447
Opus 5	$0.00048	$0.00224
Sonnet 5	$0.00019	$0.00089
Haiku 4.5	$0.00010	$0.00045

Measured 12d ago against content hash cead05db002a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

voyager-agent 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/evaluate_voyager_skill_routing.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/voyager-agent/SKILL.md · 44 lines

What it actually says

Axelera Voyager SDK Agent

Use this mode when you are developing for Axelera AI hardware with the Voyager SDK.

Instructions

Start: $ARGUMENTS

Step 0: Environment & Hardware Detection

Clarify the goal (pipeline creation, deployment, inference, benchmarking, debugging).
Confirm the target hardware and environment (Axelera device type and form factor, host OS, driver status).
Use Axelera Voyager MCP for:
- Knowledge search (docs + code examples)
- Project/task tracking for repeatable work
Recommended skills:
- voyager-launch for complete runnable pipeline/demo/package/validation requests
- voyager-init
- voyager-help
- voyager-new-pipeline, voyager-deploy, voyager-run, voyager-bench, voyager-debug

For routing ambiguity, read references/skill-routing.md.

Parallel Orchestration

See common/agent-orchestration.md for the full lane rules. For this skill:

For multi-part requests, fan out exploration and research subagents in parallel (RAG queries, repo orientation, media probing).
Route implementation work to the specialist skills; do not absorb their jobs into one serial thread.
Serialize anything that touches the Metis device into a single lane.

Files

What ships with it

10 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.

12d ago First seen · 44 lines · 95 tokens per session scan A cead05db002a

Subscribe to this mod's changes

voyager-agent is a skill published in the GitHub repository fxd0h/Axelera-Voyager-Local-Assistant (4 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 447 once invoked, about $0.0005 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 2026-08-31.

Claude Code Hardware and IoT Planning ai-agent aipu axelera computer-vision edge-ai

bubbaloop-physical-ai

Manage physical sensors, cameras, and actuators via the bubbaloop skill runtime. Query real-time sensor data, control node lifecycle, and monitor hardware health.

kornia/bubbaloop · 40 tokens

using-bubbaloop

Use when interacting with a Bubbaloop deployment via its MCP server — guides the discovery → control → automation workflow and prevents the most common mistakes (MCP polling for streaming data, missing Bearer token, ignoring RBAC tier).

kornia/bubbaloop · 53 tokens

habitat-gs-control

Interactively pilot a robot in habitat-gs 3D Gaussian Splatting indoor scenes via MCP tools — load a scene, move, observe with RGB/depth, run autonomous nav loops, and export video. Use for hands-on control of a live sim session, NOT for training or evaluating a navigation policy (use the habitat-gs-train skill for…

zju3dv/habitat-gs · 80 tokens

voyager-agent