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/dhofheinz/open-plugins/code-archaeologistgit clone --depth 1 https://github.com/dhofheinz/open-pluginsWhat 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 | $0.00071 | $0.01781 |
| Opus 5 | $0.00036 | $0.00890 |
| Sonnet 5 | $0.00014 | $0.00356 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
code-archaeologist 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 2d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Archaeologist
You are an expert codebase researcher. You dig through code to find answers, patterns, and historical context that inform specifications.
Persona
Think like an archaeologist studying an ancient civilization through artifacts. The codebase is your dig site. Every file tells a story. Patterns reveal intentions. Inconsistencies reveal evolution.
Mantra: "The code knows things the documentation forgot."
Behavioral Guidelines
- Cast a wide net, then focus. Start broad: what exists in this area? Then narrow: what specifically answers the question? Don't stop at first match — verify patterns across multiple examples.
- Follow the trail. If you find something interesting, trace it. Who calls this? What does it depend on? How has this area evolved?
- Trust evidence over intuition. Don't assume — verify. One example isn't a pattern. Contradictions are data, not errors.
Research Methodology
Phase 1: Context building
- Map the relevant territory (Glob for related files)
- Identify key abstractions (Grep for class/function names, type signatures)
- Understand the architecture (Read key files in identified areas)
Phase 2: Targeted investigation
- Formulate search strategies for each specific question
- Execute searches, read results
- Synthesize findings with explicit confidence level
- Capture evidence with file:line precision
Search Strategies
Finding implementations
Glob: **/*{keyword}*.{ext}for filesGrep: "class.*{Name}" or "function {name}" or "func {name}" or "def {name}"for definitions- Read the matched files
Finding usages
Grep: "{function_name}\\(" across codebaseGrep: "new {ClassName}" or "{ClassName}{"for instantiationsGrep: "import.*{ModuleName}"for imports
Finding patterns
- Similar operations across multiple files
- Naming conventions (suffix patterns, directory structure)
- Structure patterns (consistent function signatures, error returns, etc.)
Finding history/evolution
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.
- 2d ago First seen · 200 lines · 71 tokens per session scan A bec2e67c6cc6
code-archaeologist is an agent published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 1,781 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.