Borrowing it
Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/.claude/agents/hecras-code-archaeologist.mdgit 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/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/gpt-cmdr/ras-commander/hecras-code-archaeologist"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/hecras-code-archaeologist.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 | $0.00230 | $0.04481 |
| Opus 5.5 | $0.00092 | $0.01792 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 (88 stars, last pushed today), licensed MIT. It adds 230 tokens to every session and 4,481 once invoked, about $0.0009 per session on Opus 5.5. 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
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
msbuild
Expert agent for MSBuild and .NET build troubleshooting, optimization, and project file quality. Routes to specialized agents for performance analysis and code review. Verifies MSBuild domain relevance before deep-diving. Specializes in build configuration, error diagnosis, binary log analysis, and resolving common…
dotnet-concurrency-specialist
Expert in .NET concurrency, threading, and race condition analysis. Specializes in Task/async patterns, thread safety, synchronization primitives, and identifying timing-dependent bugs in multithreaded .NET applications. Use for analyzing racy unit tests, deadlocks, and concurrent code issues.
dotnet-async-performance-specialist
Analyzes async/await performance, ValueTask correctness, ConfigureAwait decisions, IO.Pipelines, ThreadPool tuning, and Channel selection in .NET code. Routes profiling to [skill:dotnet-performance-analyst], thread sync bugs to [skill:dotnet-csharp-concurrency-specialist].
dotnet-csharp-concurrency-specialist
Debugs race conditions, deadlocks, thread safety issues, concurrent access bugs, lock contention, async races, parallel execution problems, and synchronization issues in .NET code. Routes general async/await questions to [skill:dotnet-csharp].
dotnet-performance-analyst
Analyzes .NET profiling data, benchmark results, GC behavior, and performance bottlenecks. Interprets flame graphs, heap dumps, and benchmark comparisons. Triggers on: performance analysis, profiling investigation, benchmark regression, why is it slow, GC pressure, allocation hot path.