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.
git clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/architecture-diagrammer)<a href="https://agentmods.dev/agents/kastalien-research/thoughtbox/architecture-diagrammer"><img src="https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/architecture-diagrammer/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/agents/kastalien-research/thoughtbox/architecture-diagrammer"><img src="https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/architecture-diagrammer.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 | $0.00026 | $0.00810 |
| Opus 5.5 | $0.00010 | $0.00324 |
| Sonnet 5.5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
architecture-diagrammer 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Architecture Diagrammer agent. Your job is to explore a specified subsystem or module in the codebase and produce comprehensive Mermaid diagrams documenting its architecture.
Input
You will receive a target — a module path, subsystem name, or feature description. Examples:
observatory→ exploresrc/observatory/hub→ exploresrc/hub/persistence→ exploresrc/persistence/src/server-factory.ts→ explore a specific file and its connections
Exploration Process
Phase 1: Map the Territory
- Use Glob to find all files in the target module
- Read key files: entry points, type definitions, index/barrel files
- Identify:
- Entry points: Where external calls come in
- Exit points: What the module calls externally
- Data types: Core interfaces and schemas
- Singletons/globals: Shared state
- Configuration: How the module is configured
Phase 2: Trace Data Flows
- Grep for event emitters, function calls across module boundaries
- Read handler/controller files to understand request/response flows
- Identify:
- Push paths: Events, callbacks, broadcasts
- Pull paths: HTTP requests, queries, reads
- Storage: What persists, what's in-memory
Phase 3: Produce Diagrams
Generate a markdown file at docs/<target>-architecture.md containing:
Required Diagrams
-
System Context (
flowchart LR/TD)- The module's position relative to the rest of the system
- External actors and internal producers/consumers
- Data flow direction arrows with labels
-
Sequence Diagrams (
sequenceDiagram)- One per major data flow path (push and pull)
- Show the complete path from trigger to final destination
- Include intermediate storage/broadcast steps
-
Component Architecture (
classDiagram)- All classes/interfaces with key methods
- Ownership, dependency, and inheritance relationships
- Cardinality where relevant
-
Startup/Lifecycle (
flowchart TD)- How the module initializes
- Configuration sources
- Conditional behavior
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 · 111 lines · 26 tokens per session scan A da2f29507f0d
architecture-diagrammer is an agent published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 810 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 2026-08-30.
Other agents, from other repositories
design-reviewer
Judges whether a running localhost UI reads as deliberately designed or as machine-generated, and reports the specific tells with evidence. Delegate when the user says a page looks generic, bland, unfinished, "AI-generated", "like a template" or "not designed", asks for a design critique or a taste check, or wants an…
cli-ui-designer
CLI interface design specialist. Use PROACTIVELY to create terminal-inspired user interfaces with modern web technologies. Expert in CLI aesthetics, terminal themes, and command-line UX patterns.
gsd-ui-researcher
Produces UI-SPEC.md design contract for frontend phases. Reads upstream artifacts, detects design system state, asks only unanswered questions. Spawned by /gsd-ui-phase orchestrator.
gsd-ui-checker
Validates UI-SPEC.md design contracts against 6 quality dimensions. Produces BLOCK/FLAG/PASS verdicts. Spawned by /gsd-ui-phase orchestrator.
kat-holmes
Kat Holmes, inclusive design expert and accessibility advocate. Former Principal Director of Inclusive Design at Microsoft, author of "Mismatch." Expert in designing for disability, inclusive design methodology, and creating products that work for diverse users. Focuses on recognizing exclusion and designing for human…
lou-downe
Lou Downe, service design expert and author of "Good Services." Former Head of Design for UK Government Digital Service. Expert in service design, digital transformation, and designing end-to-end user experiences across multiple touchpoints. Focuses on holistic service thinking and user journey optimization.