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.
npx skills add Master0fFate/parallax-claudecode --skill horizongit clone --depth 1 https://github.com/Master0fFate/parallax-claudecodeWrote 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/master0ffate/parallax-claudecode/horizon)<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.
<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>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 | $0.00022 | $0.00341 |
| Opus 5.5 | $0.00009 | $0.00136 |
| Sonnet 5.5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
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 1mo 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.
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.
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.
- 1mo ago First seen · 19 lines · 22 tokens per session scan A d59904e3d419
horizon is a skill published in the GitHub repository Master0fFate/parallax-claudecode (0 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 341 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
stack-pr
Use when breaking a too-big branch into a stack of smaller chained PRs — commit-based default, --smart agent-reshape, gh-stack detection, cross-links. Invoked by /orc:stack-pr and /orc:ship's size gate.
systematic-debugging
Root-cause-first debugging discipline — build a red-capable feedback loop, minimise the repro, rank falsifiable hypotheses, fix at the source.
env-provisioning
Provision a fast, reproducible dev environment for QA or standalone use — healthcheck-gated boot, reuse/teardown rules, host-mode fallback. Protocol for /orc:env, /orc:qa Phase 4, /orc:flow Phase 6, and the orc-env-provisioner agent.
evidence-publish
Deliver a QA/evidence packet to a tracker or keep it local, behind an always-ask preview gate. Protocol for /orc:qa Phase 6, /orc:evidence, and any evidence-delivery step.
mobile-ios-design
Master iOS Human Interface Guidelines (HIG) and SwiftUI patterns to build polished, native iOS applications that feel at home on Apple platforms.
pr-size-budget
Use when opening a PR or planning slices — defines the soft 300 LOC budget, the exclusion list, the shared gate prompt for ship/flow/stack-pr, and the override syntax.