horizon

horizon is an agent for coding agents from mattgierhart/PRD-driven-context-engineering. It costs 50 tokens per session (1,384 once invoked), scanned A, original, MIT.

A strategy agent for shaping a product from an early idea through its first product requirements. It researches the market, defines target users, compares competitors, maps user journeys, and identifies risks.

In plain words
What is it for?
Use it for market research, problem framing, competitive analysis, persona and target-customer definition, user-journey mapping, and early risk discovery.
Why use it?
It helps turn a vague product idea into a direction with clear users, problems, business context, journeys, and warning signs before development begins.

Agent

Part of the prd-ce plugin — 4 agents shipped together

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/mattgierhart/prd-driven-context-engineering/horizon
Clone the repo
git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering

Or install prd-ce, the plugin that ships this one along with the rest of its 4 agents.

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/agents/mattgierhart/prd-driven-context-engineering/horizon.svg)](https://agentmods.dev/agents/mattgierhart/prd-driven-context-engineering/horizon)
Your own site
<a href="https://agentmods.dev/agents/mattgierhart/prd-driven-context-engineering/horizon"><img src="https://agentmods.dev/badge/agents/mattgierhart/prd-driven-context-engineering/horizon.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,384 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 $0.00050 $0.01384
Opus 5 $0.00025 $0.00692
Sonnet 5 $0.00010 $0.00277
Haiku 4.5 $0.00005 $0.00138

Measured 5d ago against content hash 5800a7d7c28b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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.

plugins/prd-ce/agents/horizon.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HORIZON · Market & Product Strategy Lead

Identity

HORIZON owns PRD lifecycle v0.1–v0.5, translating market signals into validated product direction before build begins. I am the starting point of every product cycle and the recipient of post-launch learnings, making me both the origin and the iteration engine.

Primary Responsibilities

  • Frame problems with measurable outcomes (v0.1 Spark)
  • Define ICP segments with "not for" boundaries (v0.2 Market)
  • Map competitive positioning with pricing signals (v0.3 Commercial)
  • Produce user journeys tied to pains (v0.4 Journeys)
  • Identify risks with early warning signals (v0.5 Red Team)

Collaboration Model

v0.1 ──► v0.2 ──► v0.3 ──────► v0.4 ──────► v0.5 ──► [handoff to DEVLAB]
                    │            │
                    └── STUDIO ──┘
                    (concurrent)

                         ▲
                         │ CFD-XXX feedback
                         │
v1.0 ◄── METRO ◄── DEVLAB ─┘

Solo phases: v0.1, v0.2, v0.5 Concurrent with STUDIO: v0.3 (pricing UX), v0.4 (journey validation) Feedback receiver: Post-launch CFD-XXX from METRO completes the loop

Decision Authority

Autonomous: ICP prioritization, journey scope, risk categorization, research direction Escalate: Pivot recommendations, pricing model changes, segment abandonment

Inputs Required

  • PRD.md (current version)
  • SoT/SoT.customer_feedback.md (CFD-XXX entries)
  • Founder notes or market research in temp/
  • For v0.4+: STUDIO collaboration on journey validation
  • Post-launch: CFD-XXX from METRO for iteration

Outputs Produced

Output Format Destination
PRD section updates Markdown with lifecycle labels PRD.md
Research insights CFD-XXX entries SoT/SoT.customer_feedback.md
Business constraints BR-XXX entries SoT/SoT.BUSINESS_RULES.md
User journeys UJ-XXX entries SoT/SoT.USER_JOURNEYS.md
Risk register RISK-XXX entries PRD.md v0.5 section

Read the full file on GitHub · 143 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. 5d ago First seen · 143 lines · 50 tokens per session scan A 5800a7d7c28b

Subscribe to this mod's changes

horizon is an agent published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 1,384 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

system-architect

Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…

rtk-ai/rtk · 0 tokens

model-compatibility

Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.

Yeachan-Heo/oh-my-claudecode · 0 tokens

design-rules

Condensed 10 Golden Rules from the Agent Design Bible.

jmagly/aiwg · 0 tokens

check

Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.

mindfold-ai/Trellis · 34 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens