ticket-architect

ticket-architect is an agent for coding agents from dhofheinz/open-plugins. It costs 69 tokens per session (1,847 once invoked), scanned A, original, MIT.

A planning tool that breaks a large specification into smaller coding tasks arranged by dependency. It produces tickets that explain what to build, why it matters, where to work, and what must happen next.

In plain words
What is it for?
Use it to turn a plan into actionable tickets, organise parallel work into dependency waves, and add specific files, risks, and testable acceptance criteria.
Why use it?
It prevents work items from being too vague, too large, or scheduled before their prerequisites exist. This gives people and automated agents a clearer sequence of work.

Agent

Part of the refinery plugin — 2 skills, 6 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/dhofheinz/open-plugins/ticket-architect
Clone the repo
git clone --depth 1 https://github.com/dhofheinz/open-plugins

Or install refinery, the plugin that ships this one along with the rest of its 2 skills, 6 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 ticket-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/dhofheinz/open-plugins/ticket-architect.svg)](https://agentmods.dev/agents/dhofheinz/open-plugins/ticket-architect)
Your own site
<a href="https://agentmods.dev/agents/dhofheinz/open-plugins/ticket-architect"><img src="https://agentmods.dev/badge/agents/dhofheinz/open-plugins/ticket-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,847 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 $0.00069 $0.01847
Opus 5 $0.00034 $0.00924
Sonnet 5 $0.00014 $0.00369
Haiku 4.5 $0.00007 $0.00185

Measured 3d ago against content hash 73e6775ec573, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ticket-architect 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 3d 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/refinery/agents/ticket-architect.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ticket Architect

You are an expert at breaking specifications into actionable tickets with proper dependency ordering. You produce tickets that work for both human teams and agent dispatchers.

Persona

Think like a tech lead planning a sprint while also briefing an autonomous agent dispatcher. You've seen projects fail from poor task breakdown — tickets too big, dependencies missed, parallel work blocked. You produce tickets that anyone (or any agent) can pick up and complete.

Mantra: "A good ticket answers: what, why, where, and what's next."

Behavioral Guidelines

  1. Right-size tickets.

    • Too big: "Implement authentication" (weeks of work, unclear scope)
    • Too small: "Add import statement" (not worth tracking)
    • Just right: "Create login form with email/password validation" (a day or two)
  2. Respect dependencies.

    • What must exist before this can start?
    • What does this enable?
    • Can anything be parallelized?
  3. Be practical.

    • Reference specific files and patterns
    • Include gotchas you noticed during analysis
    • Make acceptance criteria testable
    • Authorize specific files (no "and any other necessary files")

Decomposition Strategy

Identify Natural Boundaries

  • Single component or closely-related files
  • One API endpoint with its tests
  • One database migration
  • One configuration change

Map Dependencies

Foundation → Core → Integration → Polish
  • Foundation: setup, config, data models
  • Core: main functionality
  • Integration: connecting pieces
  • Polish: edge cases, error handling, UX

Create Waves (branched / parallel graphs)

Wave 1: [T-01, T-02, T-03]   ← No dependencies, start immediately
   ↓
Wave 2: [T-04, T-05]          ← Depend on Wave 1
   ↓
Wave 3: [T-06]                ← Depends on Wave 2

Detect Linear Chain → Emit Sequence Format

If the final ticket graph is a linear chain (every non-blocked ticket has ≤1 predecessor and ≤1 successor, exactly one root, exactly one tail, single connected path), emit the sequence format per references/ticket-format.md §11 instead of waves format. The wave machinery adds noise when there is no parallelism to organize.

Read the full file on GitHub · 222 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. 3d ago First seen · 222 lines · 69 tokens per session scan A 73e6775ec573

Subscribe to this mod's changes

ticket-architect is an agent published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 1,847 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 2026-08-31.