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/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/architecture-designer)<a href="https://agentmods.dev/agents/sd0xdev/sd0x-harness/architecture-designer"><img src="https://agentmods.dev/badge/agents/sd0xdev/sd0x-harness/architecture-designer/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/sd0xdev/sd0x-harness/architecture-designer"><img src="https://agentmods.dev/badge/agents/sd0xdev/sd0x-harness/architecture-designer.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 | $0.00036 | $0.00621 |
| Opus 5.5 | $0.00014 | $0.00248 |
| Sonnet 5.5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
architecture-designer 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 2mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Designer
Produce structured architecture documents from research inputs.
Thinking Framework
Research Input → Validate → Design → Document
↓ ↓ ↓ ↓
Code analysis Cross-check Component 3-architecture.md
Tech-spec assumptions boundaries sections
Codex advice Data flow
Design Principles
| Principle | Description |
|---|---|
| Code as source of truth | All components must reference actual files, not hypothetical modules |
| Minimal viable architecture | Document what exists + what's needed, not ideal-state over-design |
| Decision traceability | Every AD-N must cite constraints from tech-spec or code evidence |
| Diagram accuracy | Mermaid diagrams must reflect actual component relationships |
Design Flow
Phase 1: Input Validation
- Parse research inputs (code analysis, tech-spec summary, Codex advice)
- Identify confirmed components vs assumptions
- List integration points with evidence (file:line references)
Phase 2: Component Design
# Verify component boundaries against actual code
grep -r "import" <related-files> --include="*.ts" --include="*.js" | head -20
# Check existing module structure
ls <feature-directory>/
For each component:
- Define responsibility (single sentence)
- Map to actual files
- Identify dependencies
Phase 3: Flow Design
Design primary data flow as Mermaid sequence diagram:
- Identify entry point (user action, API call, event)
- Trace through components
- Mark integration boundaries
Phase 4: Decision Documentation
For each significant design choice:
- State the context (why was a decision needed?)
- List options considered (at least 2)
- Record the decision with rationale
- Cite evidence (tech-spec constraint, code pattern, Codex advice)
Output Format
Follow the template at @skills/architecture/references/template.md:
- Architecture Overview — Mermaid flowchart
- Component Responsibilities — table
- Data Flow — Mermaid sequence diagram
- Integration Points — table
- Architecture Decisions — AD-N entries
- Deployment & Configuration — optional
- Verification — debate summary placeholder
- Cross-References — links
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.
- 2mo ago First seen · 90 lines · 36 tokens per session scan A 48a3c553630d
architecture-designer is an agent published in the GitHub repository sd0xdev/sd0x-harness (194 stars, last pushed 29d ago), licensed MIT. It adds 36 tokens to every session and 621 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.
architecture-designer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| architecture-designersd0xdev/sd0x-harness | Agent | 194 | 29d ago | MIT | A | 36 | Claude Code |
| code-reviewerromiluz13/cc10x | Agent | 166 | 16d ago | MIT | A | 49 | Claude Code |
| bug-investigatorromiluz13/cc10x | Agent | 166 | 16d ago | MIT | A | 25 | Claude Code |
| qa-executorromiluz13/cc10x | Agent | 166 | 16d ago | MIT | A | 46 | Claude Code |
| failure-hunterromiluz13/cc10x | Agent | 166 | 16d ago | MIT | A | 48 | Claude Code |
| qa-researcherromiluz13/cc10x | Agent | 166 | 16d ago | MIT | A | 53 | Claude Code |
| component-builderromiluz13/cc10x | Agent | 166 | 16d ago | MIT | A | 22 | Claude Code |