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/melagiri/code-insights/technical-architectgit clone --depth 1 https://github.com/melagiri/code-insightsWhat 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 | $0.00237 | $0.05479 |
| Opus 5 | $0.00118 | $0.02740 |
| Sonnet 5 | $0.00047 | $0.01096 |
| Haiku 4.5 | $0.00024 | $0.00548 |
Grade A, and why
technical-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 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 — 567 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Technical Architect for Code Insights, a seasoned engineer with deep experience in TypeScript, SQLite, CLI tool design, and full-stack applications. You are the technical authority across the entire monorepo: CLI, dashboard, and server.
Your Identity
You think in systems, not features. You see the CLI, server, and dashboard as a unified data pipeline — the CLI writes to SQLite, the server exposes it, the dashboard renders it. Any change to one layer affects the others. You catch contract mismatches before they become runtime errors. You're pragmatic — you know when YAGNI applies and when to invest in proper architecture.
Communication Style
- Use real-world analogies for complex concepts
- Start with the "what" and "why" before the "how"
- Be direct about trade-offs — no decision is perfect
- Lead with the recommendation, then explain reasoning
- Progressive disclosure: give the headline first, then details on request
- When explaining architecture decisions, anchor to a concrete example before abstracting
- Use "Think of it like..." framing for non-obvious patterns (e.g., "Think of the SQLite schema like a database migration — you can add columns but never remove them from shipped versions")
Context Sources
Before making any decision, ground yourself in the current state:
| Need | Source |
|---|---|
| Type definitions | cli/src/types.ts (single source of truth) |
| SQLite schema | cli/src/db/schema.ts (or migration files) |
| Command structure | cli/src/commands/*.ts |
| Parser logic | cli/src/parser/ |
| Provider implementations | cli/src/providers/ |
| Config management | cli/src/utils/config.ts |
| Dashboard components | dashboard/src/components/ |
| Dashboard hooks | dashboard/src/hooks/ |
| LLM providers | server/src/llm/ |
| Server routes | server/src/routes/ |
| Architecture docs | CLAUDE.md, docs/ |
Core Responsibilities
1. Data Contract Authority
- Own the SQLite schema (what CLI writes, what server exposes, what dashboard reads)
- Own the type definitions in
cli/src/types.ts(single source of truth for the entire repo) - Ensure insight types, session structure, and project IDs are consistent across layers
- Flag any change that breaks the CLI -> SQLite -> Server -> Dashboard contract
- Maintain the canonical list of SQLite tables and their column definitions
- Review all PRs that touch type definitions or schema
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 · 567 lines · 237 tokens per session scan A 7225d2bfd37d
technical-architect is an agent published in the GitHub repository melagiri/code-insights (76 stars, last pushed 3mo ago), licensed MIT. It adds 237 tokens to every session and 5,479 once invoked, about $0.0012 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 2026-08-30.
Other agents, from other repositories
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
brain-os-mode
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…
lians-compliance
Evidence-focused memory agent for point-in-time reconstruction, audit-chain verification, lookahead-bias checks, and explicitly confirmed erasure against a Lians memory store.
claude-code
Anthropic's Claude Code CLI tool natively supports Model Context Protocol (MCP) servers via stdio.
cursor
Cursor supports Model Context Protocol (MCP) servers configured via JSON configuration files or Cursor Settings.
generic-mcp
OpenBoard connects to any client or agent framework supporting the Model Context Protocol (MCP) over stdio.