reference-builder

reference-builder is an agent for Claude Code from NOMARJ/sigil. It costs 41 tokens per session (1,188 once invoked), scanned A, original, Apache-2.0.

A technical-reference writer that creates detailed API, configuration, schema, and specification documentation.

In plain words
What is it for?
Use it for API references, configuration guides, schema documentation, searchable specifications, and complete parameter listings.
Why use it?
It organizes exact options, parameters, return values, constraints, dependencies, examples, and edge cases so developers can look up how something works.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it for API references, configuration guides, schema documentation, searchable specifications, and complete parameter listings.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nomarj/sigil/reference-builder
Install

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.

Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil

Made for: Claude Code.

Wrote 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.

agentmods badge for reference-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/nomarj/sigil/reference-builder.svg)](https://agentmods.dev/agents/nomarj/sigil/reference-builder)
Your own site
<a href="https://agentmods.dev/agents/nomarj/sigil/reference-builder"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/reference-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,188 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01188
Opus 5 $0.00020 $0.00594
Sonnet 5 $0.00008 $0.00238
Haiku 4.5 $0.00004 $0.00119

Measured 3d ago against content hash 8d8c4ae50bd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 3d 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.

packs/quality/agents/reference-builder.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 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

  1. Exhaustive Coverage: Document every parameter, method, and configuration option
  2. Precise Categorization: Organize information for quick retrieval
  3. Cross-Referencing: Link related concepts and dependencies
  4. Example Generation: Provide examples for every documented feature
  5. 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

  1. Overview: Quick introduction to the module/API
  2. Quick Reference: Cheat sheet of common operations
  3. Detailed Reference: Alphabetical or logical grouping
  4. Advanced Topics: Complex scenarios and optimizations
  5. Appendices: Glossary, error codes, deprecations

Read the full file on GitHub · 188 lines

Changes

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.

  1. 3d ago First seen · 188 lines · 41 tokens per session scan A 8d8c4ae50bd7

Subscribe to this mod's changes

reference-builder is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 1,188 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 2026-09-04.

Related

Other agents, from other repositories

ocr-grammar-fixer

You are an OCR Grammar Fixer specializing in cleaning up text processed through OCR that contains recognition errors, spacing issues, or grammatical problems. Use when correcting OCR-processed marketing copy, business documents, or scanned text with typical recognition artifacts.

davepoon/buildwithclaude · 53 tokens

ocr-quality-assurance

You are an OCR Quality Assurance specialist performing final review and validation of OCR-corrected text against original image sources. Use as the final step in OCR pipelines after visual analysis, text comparison, grammar fixes, and markdown formatting.

davepoon/buildwithclaude · 50 tokens

visual-analysis-ocr

Extract and analyze text content from PNG images while preserving original formatting and structure. Converts visual hierarchy into markdown format.

davepoon/buildwithclaude · 27 tokens

metadata-agent

Handles frontmatter standardization and metadata addition across vault files. Ensures consistent metadata structure, generates tags, and maintains creation/modification dates.

davepoon/buildwithclaude · 31 tokens

text-comparison-validator

Compare extracted text from images with existing markdown files to ensure accuracy and consistency. Detects discrepancies, errors, and formatting inconsistencies.

davepoon/buildwithclaude · 31 tokens

tag-agent

Normalizes and hierarchically organizes tag taxonomy for knowledge management systems. Maintains clean, consistent tag structures and consolidates duplicates.

davepoon/buildwithclaude · 29 tokens