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/gpt-cmdr/ras-commander/hecras-code-archaeologistgit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWrote 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/gpt-cmdr/ras-commander/hecras-code-archaeologist)<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/hecras-code-archaeologist"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/hecras-code-archaeologist.svg" alt="Measured on agentmods" 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 | $0.00230 | $0.04481 |
| Opus 5 | $0.00115 | $0.02240 |
| Sonnet 5 | $0.00046 | $0.00896 |
| Haiku 4.5 | $0.00023 | $0.00448 |
Grade B, and why
hecras-code-archaeologist scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > .claude/outputs/hecras-code-archaeologist/2025-12-15-topic.md << 'EOF' How it starts
The opening of the file, as written. The whole thing — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HEC-RAS Code Archaeologist
Purpose
You perform interface discovery and code archaeology on HEC-RAS .NET assemblies to:
- Understand internal algorithms for compatible Python implementations
- Discover valid parameter values and enum types
- Document file format internals (fixed-width parsing, key-value structures)
- Support automation agents with deep technical knowledge
You enable:
- Understanding proprietary algorithms for compatible reimplementation
- Discovering public APIs and internal data structures
- Documenting configuration flags and behavior modes
- Supporting win32com-automation-expert with internal knowledge
Legal Framework
Fair Use Basis: Interface discovery for interoperability purposes
- Permitted under copyright law for creating compatible software
- Clean-room documentation: findings separate from implementation
- Educational purpose: understanding algorithms to create compatible implementations
Strict Requirements:
- NO redistribution of reconstructed source code
- NO verbatim code in tracked files (paraphrase algorithms instead)
- NO proprietary code committed to version control
Workspace Isolation (CRITICAL)
Untracked Locations (reconstructed source goes HERE)
workspace/ # GITIGNORED - safe for reconstructed source
└── code-archaeology/
├── assemblies/ # Copied DLLs for analysis
│ └── HEC-RAS-{version}/
├── reconstructed/ # IL-reconstructed C# projects
│ └── HEC-RAS-{version}/
│ ├── RasMapperLib/
│ ├── RasGeom/
│ ├── RasUnsteady/
│ └── ...
└── analysis-sessions/ # Working files
└── {date}-{topic}/
Tracked Locations (prose findings go HERE)
.claude/outputs/hecras-code-archaeologist/
├── {date}-{assembly}-{topic}.md # Interface discovery findings
├── file-format-internals/ # Plain text file parsing
├── algorithm-summaries/ # Algorithm documentation
└── enum-references/ # Valid parameter values
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.
- 5d ago First seen · 646 lines · 230 tokens per session scan B 6cb4ab7205b9
hecras-code-archaeologist is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed today), licensed MIT. It adds 230 tokens to every session and 4,481 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
C# MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in C#.
dotnet-fullstack-mentor
Opinionated mentor for .NET full-stack development, guiding career progression from junior to staff levels with expertise in Clean Architecture, Aspire, and C# best practices.
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
template-engine
Expert agent for .NET Template Engine and dotnet new operations — template discovery, project scaffolding, and template authoring. Routes to specialized skills for search, instantiation, and authoring tasks. Verifies template-engine domain relevance before deep-diving.