horizon

horizon is a skill for Claude Code from Master0fFate/parallax-claudecode. It costs 22 tokens per session (341 once invoked), scanned A, original, MIT.

A workflow for carrying out a large goal made up of several software features. It keeps a durable plan, research notes, progress records, verification results, and an audit trail while allowing a limited number of automatic retries.

In plain words
What is it for?
Use it for multi-feature implementation, refactoring, architecture, security work, and other complex changes that need planning, delegated workers, checks, and recorded decisions.
Why use it?
Large coding tasks can lose track of decisions, unfinished work, or failed checks. This workflow breaks the goal into measurable pieces and pauses when a result needs correction or an outside resource.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the parallax-claudecode plugin — 9 skills, 1 command, 4 agents, 12 hooks, 1 MCP server shipped together

Good fit Use it for multi-feature implementation, refactoring, architecture, security work, and other complex changes that need planning, delegated workers, checks, and recorded decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/master0ffate/parallax-claudecode/horizon
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 Master0fFate/parallax-claudecode --skill horizon
Clone the repo
git clone --depth 1 https://github.com/Master0fFate/parallax-claudecode

Made for: Claude Code.

Or install parallax-claudecode, the plugin that ships this one along with the rest of its 9 skills, 1 command, 4 agents, 12 hooks, 1 MCP server.

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.

agentmods badge for horizon

README.md
[![agentmods](https://agentmods.dev/badge/skills/master0ffate/parallax-claudecode/horizon/github.svg)](https://agentmods.dev/skills/master0ffate/parallax-claudecode/horizon)
Your own site
<a href="https://agentmods.dev/skills/master0ffate/parallax-claudecode/horizon"><img src="https://agentmods.dev/badge/skills/master0ffate/parallax-claudecode/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.

agentmods 80×15 button for horizon

Your own site · 80×15
<a href="https://agentmods.dev/skills/master0ffate/parallax-claudecode/horizon"><img src="https://agentmods.dev/badge/skills/master0ffate/parallax-claudecode/horizon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 341 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00341
Opus 5 $0.00011 $0.00170
Sonnet 5 $0.00004 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 8d ago against content hash d59904e3d419, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 8d 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.

skills/horizon/SKILL.md · 19 lines

What it actually says

Horizon

Switch the current core session with parallax_horizon. For $ARGUMENTS, resume only an explicitly matching Horizon session or initialize a unique ID with horizon_init_session.

Research first and persist concise findings. Write a schema-valid milestone and feature plan with measurable acceptance criteria. Use full Parallax protocol for implementation, refactors, architecture, security, and complex fixes; use none only for bounded research or trivial changes.

Execute one feature at a time. Keep plan and orchestration state synchronized and log consequential autonomous decisions. Evaluate each result with horizon_evaluate_subagent; it independently runs detected project checks and derives the verification dimension rather than trusting caller prose. Passing checks and an aggregate score of at least 75 are required; otherwise run a corrective pass. Never exceed the configured retry cap. Pause mid-run only for an external resource or authorization that cannot be researched or safely defaulted.

When dispatching parallax-claudecode:horizon-worker or parallax-claudecode:horizon-auditor, the first prompt line must be exactly HORIZON_DISPATCH {"sessionId":"<horizon-session>","featureId":"<feature>"} followed by the brief. A human brief alone is rejected because it has no durable session/feature identity.

Complete with a final debug audit, broad verification, archived traces where useful, consistent completion stats, and an honest report of completed, failed, and deferred work.

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. 8d ago First seen · 19 lines · 22 tokens per session scan A d59904e3d419

Subscribe to this mod's changes

horizon is a skill published in the GitHub repository Master0fFate/parallax-claudecode (0 stars, last pushed 15d ago), licensed MIT. It adds 22 tokens to every session and 341 once invoked, about $0.0001 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.