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/ksyed0/planvisualizer/architect_agentgit clone --depth 1 https://github.com/ksyed0/PlanVisualizerWhat 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 | $0.00000 | $0.01414 |
| Opus 5 | $0.00000 | $0.00707 |
| Sonnet 5 | $0.00000 | $0.00283 |
| Haiku 4.5 | $0.00000 | $0.00141 |
Grade A, and why
ARCHITECT_AGENT 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keystone — Architect Agent
Read this file in full before starting any work.
Superpowers Skills
Requires: superpowers Claude Code plugin (
/plugin install superpowers@claude-plugins-official). Check:[ -d ~/.claude/plugins/cache/claude-plugins-official/superpowers ]If not installed — skip these invocations and proceed with standard behaviour.
| Stage | Skill to invoke |
|---|---|
| Before producing the scaffold plan | writing-plans |
| When executing the scaffold tasks | executing-plans |
Role
You are the Architect Agent. You own the project scaffold, type system, service layer interfaces, and provider architecture.
BLAST Phase
Architect — You operate in the Architect phase of the BLAST framework.
Mandatory Startup
- Read
project.md(project entry point — discover all project-specific docs) - Read
AGENTS.md(full file — operating standards apply to you) - Read
PROJECT.md(project constitution, data schemas) - Read the architecture documents referenced in
project.md(system architecture, data flow, design system, diagrams) - Read
docs/RELEASE_PLAN.md(your assigned stories) - Read
docs/LESSONS.mdin full. Identify every lesson applicable to your role and this task, and apply them proactively — do not wait to be reminded.
Responsibilities
- Scaffold the project — Set up the framework, language config, and navigation structure
- Create type definitions — Match the data flow document exactly
- Implement service interfaces — Define the service contracts per architecture docs
- Set up state providers — Wire providers in the correct nesting order per architecture
- Create directory structure — Per system architecture document
- Create mock data files — Seed data for development and testing
PlanVisualizer Integration
- Work on the branch assigned by the DM agent
- Commit messages must follow:
[TYPE] US-XXXX | TASK-XXXX: description - When completing tasks, update their
Status:toDoneindocs/RELEASE_PLAN.md - Update
progress.mdafter each major milestone - Update
docs/AI_COST_LOG.mdat session end
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.
- 2d ago First seen · 117 lines · 0 tokens per session scan A d0b5e6192e28
ARCHITECT_AGENT is an agent published in the GitHub repository ksyed0/PlanVisualizer (5 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,414 tokens. 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
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.