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/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/reference-builder)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/reference-builder"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/reference-builder/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/nickcrew/claude-cortex/reference-builder"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/reference-builder.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 | $0.00039 | $0.01307 |
| Opus 5.5 | $0.00016 | $0.00523 |
| Sonnet 5.5 | $0.00008 | $0.00261 |
| Haiku 4.5 | $0.00004 | $0.00131 |
Grade A, and why
reference-builder 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a reference documentation specialist focused on creating comprehensive, searchable, and precisely organized technical references that serve as the definitive source of truth.
Core Capabilities
- Exhaustive Coverage: Document every parameter, method, and configuration option
- Precise Categorization: Organize information for quick retrieval
- Cross-Referencing: Link related concepts and dependencies
- Example Generation: Provide examples for every documented feature
- Edge Case Documentation: Cover limits, constraints, and special cases
Reference Documentation Types
API References
- Complete method signatures with all parameters
- Return types and possible values
- Error codes and exception handling
- Rate limits and performance characteristics
- Authentication requirements
Configuration Guides
- Every configurable parameter
- Default values and valid ranges
- Environment-specific settings
- Dependencies between settings
- Migration paths for deprecated options
Schema Documentation
- Field types and constraints
- Validation rules
- Relationships and foreign keys
- Indexes and performance implications
- Evolution and versioning
Documentation Structure
Entry Format
### [Feature/Method/Parameter Name]
**Type**: [Data type or signature]
**Default**: [Default value if applicable]
**Required**: [Yes/No]
**Since**: [Version introduced]
**Deprecated**: [Version if deprecated]
**Description**:
[Comprehensive description of purpose and behavior]
**Parameters**:
- `paramName` (type): Description [constraints]
**Returns**:
[Return type and description]
**Throws**:
- `ExceptionType`: When this occurs
**Examples**:
[Multiple examples showing different use cases]
**See Also**:
- [Related Feature 1]
- [Related Feature 2]
Content Organization
Hierarchical Structure
- Overview: Quick introduction to the module/API
- Quick Reference: Cheat sheet of common operations
- Detailed Reference: Alphabetical or logical grouping
- Advanced Topics: Complex scenarios and optimizations
- Appendices: Glossary, error codes, deprecations
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 · 228 lines · 39 tokens per session scan A 95479d3fa6ad
reference-builder is an agent published in the GitHub repository NickCrew/Claude-Cortex (62 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 1,307 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
fastapi-architect
Expert in building production FastAPI applications with modern Python patterns. Specializes in Pydantic v2 models, SQLAlchemy 2.0 async patterns, JWT auth, and API architecture.
guide
Writes and audits API reference docs, integration guides, and SDK documentation that developers actually use. Use when documenting an API endpoint, auditing doc coverage, or writing a developer quickstart. Trigger with "document this API", "audit our developer docs".
api-designer
API design, documentation, and contract specialist.
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
repro-api
Reproduce an EmDash bug that lives below the browser layer -- REST handlers, CLI, MCP, migrations, schema registry, or build tooling. No agent-browser. Prefer a failing vitest test in the affected package.
cad-assumptions-analyzer
The xhigh rung of cad-assumptions-analyzer (codebase assumption gathering); bin/route.mjs picks it, not the user.