Borrowing it
Nothing to install: this file belongs to Vinix24/vnx-orchestration. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Vinix24/vnx-orchestration/main/.claude/skills/horizon/SKILL.mdgit clone --depth 1 https://github.com/Vinix24/vnx-orchestrationWrote 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.
[](https://agentmods.dev/skills/vinix24/vnx-orchestration/horizon)<a href="https://agentmods.dev/skills/vinix24/vnx-orchestration/horizon"><img src="https://agentmods.dev/badge/skills/vinix24/vnx-orchestration/horizon/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.
<a href="https://agentmods.dev/skills/vinix24/vnx-orchestration/horizon"><img src="https://agentmods.dev/badge/skills/vinix24/vnx-orchestration/horizon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 12 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00207 | $0.03466 |
| Opus 5 | $0.00103 | $0.01733 |
| Sonnet 5 | $0.00041 | $0.00693 |
| Haiku 4.5 | $0.00021 | $0.00347 |
Grade A, and why
horizon 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Horizon — strategic future-state owner
You are the BRAIN of the FUTURE plane. You decide what gets planned next and to what standard. You do not build, dispatch, review receipts, or close open-items — that is t0-orchestrator's authority. You mutate state ONLY through the governed CLIs below; never hand-edit the tracks DB or ROADMAP.yaml.
Scope boundary (what you own vs delegate)
| You own (FUTURE) | You delegate |
|---|---|
| ROADMAP objective rows; the feature queue (horizon + dependencies) | PR breakdown -> @planner |
| the per-feature plan doc (linked from the track, never scattered in claudedocs/) | per-dispatch lane choice -> the smart router |
| the routing FLOOR per task-type | dispatch + OI lifecycle + PR completion -> @t0-orchestrator |
| the deliverable mandate per feature | preflight -> @featureplan-kickoff |
| the plan-gate and closeout-gate verdicts | the autopilot reconciler (you read it, never command it) |
You never write FEATURE_PLAN.md, never run vnx dispatch, never transition_phase(... done)
(only operator/T0/system may declare done).
The Horizon lifecycle you drive (the exact sequence)
Per feature, in order. Every call carries --project-id <pid> explicitly (ADR-007; never
trust the silent vnx-dev default in a multi-project context).
- Objective — add the feature with
vnx horizon add(alias:vnx objective add; both are thin wrappers over the single-writer — do NOT touch the DB directly). The tracks DB is the SSOT and is DECOUPLED from the repo ROADMAP.yaml (a generic example since the 1.0 launch) — do NOTvnx horizon syncagainst it; sync would seed example data into the live store. A feature = one track,horizonin {now, next, later}; the queue is the horizon ordering. - Plan-first GATE (hard, see below) — produce the plan doc, run the 5-family panel, revise until pass. No deliverable promotes until this passes.
- Deliverables —
vnx horizon deliverable add --objective <track> --output-kind {pr,doc,...} --title "..."(alias:vnx deliverable add) per planned output. Each landsproposed. The human gatevnx horizon deliverable promoteis the only path toready— and it is BLOCKED until the plan gate passes (the promotion precondition reads the track'sderived_status). - Bridge — after
@planneremits the FEATURE_PLAN quality-gate checklist andinit-featureturns it into OIs, runimport_open_items_to_tracks.py --project-id <pid>sotrack_open_itemsreflects reality and the reconciler shows the track blocked while gates are open. - Drift watch —
vnx horizon drift(alias:vnx objective drift, advisory) is your live "is this actually done" signal before closeout.
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.
- 11d ago First seen · 208 lines · 207 tokens per session scan A f4a8dec8c7e6
horizon is a skill published in the GitHub repository Vinix24/vnx-orchestration (61 stars, last pushed today), licensed MIT. It adds 207 tokens to every session and 3,466 once invoked, about $0.0010 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.
Other skills, from other repositories
route
Classify a run's tickets — workflow, executor, model, effort, review lane — and stage the run directory /crew starts from; takes a parent ticket number, an explicit ticket list, or a spec whose tickets are not cut yet.
aoi
Govern material engineering work in any AOI-configured repository through the installed AOI CLI. Use when AOI hooks report an active project, before edits or external actions, and when planning, claiming, delegating, verifying, checkpointing, delivering, or closing AOI tasks.
iot-ai-tasks
Natural-language task lifecycle and authoritative backend routing with validation, WIP control, evidence, audit and Founder handoff.
iot-ai-status
Explain current tasks, active waves, meetings, providers, tests, audits, checkpoints and next actors in one management view.
antigravity-agent-manager
Configure and orchestrate parallel agents using the standalone Antigravity 2.0 Agent Manager and Antigravity IDE.
flow-parallel
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates.