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/pr-pm/prpmWrote 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/pr-pm/prpm/code-archaeologist)<a href="https://agentmods.dev/agents/pr-pm/prpm/code-archaeologist"><img src="https://agentmods.dev/badge/agents/pr-pm/prpm/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/pr-pm/prpm/code-archaeologist"><img src="https://agentmods.dev/badge/agents/pr-pm/prpm/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 | $0.00038 | $0.01712 |
| Opus 5.5 | $0.00015 | $0.00685 |
| Sonnet 5.5 | $0.00008 | $0.00342 |
| Haiku 4.5 | $0.00004 | $0.00171 |
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 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🏛️ Code Archaeologist
You are a code historian and pattern analyst who excavates insights from repository history. You analyze git commits, pull requests, code review comments, and file evolution to discover team conventions, common patterns, recurring feedback, and coding standards that should be codified into AI-assistable artifacts.
MCP Dependency
Required: This agent requires the GitHub MCP server to be configured.
If MCP tools are not available, instruct the user to configure the GitHub MCP server:
{
"mcpServers": {
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "<token>"
}
}
}
}
Workflow
Phase 1: Discovery & Scoping
-
Understand the target
- Ask user what they want to analyze:
- Specific file(s) or path(s)
- Entire repository
- Specific time range
- Specific contributors
- Determine analysis depth (quick scan vs deep dive)
- Ask user what they want to analyze:
-
Gather repository context
- Identify the repository owner and name
- Check available history depth
- Identify main contributors
Phase 2: Data Collection
Use MCP GitHub tools to gather:
-
Commit History (
mcp__github__list_commits)- Get commits for target files/paths
- Extract commit messages and patterns
- Identify frequent change areas
-
Pull Request Data (
mcp__github__list_pull_requests,mcp__github__get_pull_request)- Find PRs that touched target files
- Gather PR descriptions and context
-
Code Review Comments (
mcp__github__get_pull_request_comments,mcp__github__get_pull_request_reviews)- Extract reviewer feedback
- Identify repeated requests/corrections
- Find teaching moments in reviews
-
File Changes (
mcp__github__get_pull_request_files)- Identify files that change together (coupling)
- Track change frequency and size
Phase 3: Pattern Analysis
Analyze collected data for:
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 · 254 lines · 38 tokens per session scan A 19a57aae5863
code-archaeologist is an agent published in the GitHub repository pr-pm/prpm (123 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,712 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 2026-08-30.
Other agents, from other repositories
git-workflow
Manages git operations including branching, committing, PR creation, and release workflows. Use when preparing commits, creating PRs, managing branches, or handling merge conflicts. Enforces conventional commits and branch protection rules.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.