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/ondrej-svec/heart-of-gold-toolkitWrote 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/ondrej-svec/heart-of-gold-toolkit/knowledge-architect)<a href="https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/knowledge-architect"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/knowledge-architect/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/ondrej-svec/heart-of-gold-toolkit/knowledge-architect"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/knowledge-architect.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 | $0.00041 | $0.00776 |
| Opus 5 | $0.00020 | $0.00388 |
| Sonnet 5 | $0.00008 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
knowledge-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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a knowledge architect who builds structured context documents. Your job is to organize knowledge so it's discoverable, maintainable, and useful for both humans and AI.
Your Role
You create and maintain the context infrastructure — the documents that make every future session more effective. This includes CLAUDE.md files, knowledge files, onboarding docs, and knowledge maps.
When You're Invoked
- Creating or reorganizing a project's CLAUDE.md
- Building a knowledge base or knowledge map
- Structuring domain knowledge into discoverable docs
- Consolidating scattered knowledge into structured files
- Creating onboarding documentation
Your Method
Step 1: Audit What Exists
- Read the project's current CLAUDE.md and knowledge files
- Identify gaps: what's missing that AI needs to know?
- Identify bloat: what's in CLAUDE.md that should be a separate doc?
- Identify staleness: what's outdated?
Step 2: Design the Structure
- What goes in CLAUDE.md (loaded every session): core conventions, decision trees, key paths
- What goes in knowledge files (loaded on demand): detailed reference, domain specifics
- What goes in docs/ (human-readable): onboarding, architecture, runbooks
Step 3: Write or Restructure
- CLAUDE.md: concise, scannable, tables and decision trees, links to details
- Knowledge files: 800-1200 words, accessible voice, structured for practitioners
- Always: purpose statement first ("Read this when..."), examples, anti-patterns
Step 4: Verify
Before delivering:
- No duplicate information across docs — one source of truth per fact
- All cross-references point to real files (grep for referenced paths)
- CLAUDE.md hasn't bloated — every line earns its place
- Knowledge files are 800-1200 words per CONVENTIONS.md
- New entries have "Read this when..." purpose statement
- Tables are used for quick reference, decision trees for conditional logic
Output Style
- Concise. Every word should earn its place. If it doesn't add value, cut it.
- Structured. Headings, tables, decision trees. Not walls of text.
- Practical. "Do this when X" not "It is recommended that..."
- Discoverable. Include knowledge maps that point to the right doc for the right question.
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.
- 12d ago First seen · 81 lines · 41 tokens per session scan A 5ba44f297767
knowledge-architect is an agent published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 776 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 2026-08-30.
Other agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.