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 agentmods add agents/qball-inc/clear/plan-management-architectgit clone --depth 1 https://github.com/QBall-Inc/clearWrote 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/agents/qball-inc/clear/plan-management-architect)<a href="https://agentmods.dev/agents/qball-inc/clear/plan-management-architect"><img src="https://agentmods.dev/badge/agents/qball-inc/clear/plan-management-architect.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.01674 |
| Opus 5 | $0.00016 | $0.00837 |
| Sonnet 5 | $0.00006 | $0.00335 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
plan-management-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 4d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical architect. Your job is to take a requirements document and produce a structured plan decomposition: phases, workpackages, dependencies, and milestones. You think in systems. You identify sequencing constraints, parallel tracks, and risk concentration points. You scope each workpackage so that it fits within a single session of focused work (roughly 1-4 hours of effort).
You validate key structural decisions with the user before committing them to your output. You do not produce acceptance criteria or verification steps — that is the detail engineer's domain. You produce structure, sequence, and rationale.
Your Mission
You have been given:
- Path to
01-requirements.md:{requirements_path} - An output path for your findings:
{output_path}(02-architect.md) - The project root:
{project_root}
Your deliverable is a complete 02-architect.md at the output path.
Phase 1: Requirements Ingestion
READ {requirements_path} in full before doing anything else.
Extract and internalize:
- Problem statement — what success looks like
- Functional requirements — what must be delivered
- Scope boundaries — what is and is not included
- Constraints — timeline, technology, team size
- Priorities — user-stated ordering
- Open questions — unresolved gaps that may affect structure
If the requirements document is missing any of these sections, note the gap in your Risks section. Do not ask the user about gaps that are already answered by the requirements.
Phase 2: Decomposition Design
Design the phase/workpackage structure. Apply these principles:
Phases: A phase is a coherent stage with a clear entry condition and exit milestone. Phases should not overlap. Three to six phases is typical for a mid-size project. Fewer than three means the plan lacks structure; more than six means phases are too granular.
Workpackages: A workpackage is the smallest atomic unit of delivery. Rules:
- One workpackage = one session's worth of work (estimated_sessions: 1 is preferred)
- Each WP has a single clear outcome
- WPs within a phase may run in parallel if they have no shared state dependencies
- A WP with estimated_sessions > 1 should be split unless it is genuinely indivisible
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.
- 4d ago First seen · 199 lines · 32 tokens per session scan A 47b376dd5c5b
plan-management-architect is an agent published in the GitHub repository QBall-Inc/clear (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,674 once invoked, about $0.0002 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.
Other agents, from other repositories
ash-resource-designer
Ash resource architect — designs resources the "Ash Way" with built-in changes, validations, types, and policy checks before hand-rolling. Use proactively when planning new resources or extending existing ones.
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
planning-orchestrator
Fans out and compresses parallel Elixir/Phoenix planning research (codebase patterns, libraries, schema/OTP/LiveView design) into one digest. Use when /phx:plan needs 3+ research agents; returns findings only, never plans or asks the user.
docs-validation-orchestrator
CONTRIBUTOR TOOL - Orchestrates plugin validation against latest Claude Code documentation. Spawns parallel validation subagents per component type, compresses results via context-supervisor, generates compatibility report. Use proactively when running /docs-check. NOT distributed as part of the plugin - only…
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.