ROADMAP

A historical roadmap of OmniLink agents and demos that were considered worth building, with notes about what shipped or was retired. It is a planning record rather than a current list of available agents.

In plain words
What is it for?
Use it to review the old build queue, understand the status of past demos, find transferable design lessons, and locate removed work in version-control history.
Why use it?
It helps explain past development priorities and preserves design lessons from earlier work. The document also warns when referenced agents, worlds, or paths no longer exist in the current tree.

Agent

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 agents/omnilink-tech/omnisim/roadmap
Clone the repo
git clone --depth 1 https://github.com/omnilink-tech/omnisim
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,256 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.03256
Opus 5 $0.00000 $0.01628
Sonnet 5 $0.00000 $0.00651
Haiku 4.5 $0.00000 $0.00326

Measured 2d ago against content hash c544540368b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ROADMAP 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.

agents/ROADMAP.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Demo roadmap — what to build next

Status (2026-07): this build queue is complete — kept as a historical record of the 2026-05 wave. Warehouse Foreman, Patrol Squad, and Drone Surveyor all shipped in that wave (Drone Surveyor iter 0–2; its iter-3 operator-chat LLM run never happened). All three were RETIRED in v5.3.0 — sections 1–3 below are a historical record, not a current inventory.

⚠️ Warehouse Foreman, Warehouse Picker and Patrol Squad were REMOVED from the tree on 2026-07-19, and ship as RETIRED in v5.3.0, along with their worlds (warehouse_logistics.wbt, warehouse_patrol.wbt). Their shipped results rested on locomotion numbers that predated the wedge-recovery teleport removal (b18bd7a3) and were never re-measured. Sections 1 and 2 below are kept as a historical record, and the production/warehouse_* paths they name are no longer in the tree — recover them from git history if you need them. The transferable design lessons survive in AGENT_PATTERNS.md.

⚠️ Drone Surveyor was REMOVED from the tree on 2026-07-22, and ships as RETIRED in v5.3.0. agents/production/drone_surveyor/ is gone; section 3 below is kept as a historical record, and the paths it names are no longer in the tree — recover them from git history if you need them. Its world, chat/omnilink_mavic.omniworld, and its bridge, mavic_omnilink_bridge, were kept — they still serve the Mavic chat demo.

For the current agent inventory, see README.md.

Working list of OmniLink agents + demos worth shipping after the husky_maze + mission_captain pair. Ordered roughly by cool-to-effort ratio. Pick the next one off the top, build it end-to-end, ship it, then come back to this list.

The bar for inclusion: each demo must do at least one thing only OmniLink can do well — multi-agent orchestration, cross-session memory dividend, natural-language brief interpretation, or visual-reasoning-driven navigation. Pure motion demos belong in stock OmniSim samples; this is the agent showcase.

Read the full file on GitHub · 159 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 · 159 lines · 0 tokens per session scan A c544540368b6

Subscribe to this mod's changes

ROADMAP is an agent published in the GitHub repository omnilink-tech/omnisim (82 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,256 tokens. 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.