code-archaeologist

A repository-history analyst that examines Git commits, pull requests, code reviews, and file changes to find a team's coding habits.

In plain words
What is it for?
Use it to study a repository or selected history and create skills, rules, or agents based on recurring patterns and review feedback.
Why use it?
It helps recover useful conventions from past work instead of relying only on undocumented assumptions.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/pr-pm/prpm/code-archaeologist
Clone the repo
git clone --depth 1 https://github.com/pr-pm/prpm

Made for: Claude Code.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.01712
Opus 5 $0.00019 $0.00856
Sonnet 5 $0.00008 $0.00342
Haiku 4.5 $0.00004 $0.00171

Measured yesterday against content hash 19a57aae5863, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

.claude/agents/code-archaeologist.md · 254 lines

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

  1. 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)
  2. 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:

  1. Commit History (mcp__github__list_commits)

    • Get commits for target files/paths
    • Extract commit messages and patterns
    • Identify frequent change areas
  2. Pull Request Data (mcp__github__list_pull_requests, mcp__github__get_pull_request)

    • Find PRs that touched target files
    • Gather PR descriptions and context
  3. 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
  4. 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:

Read the full file on GitHub · 254 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. yesterday First seen · 254 lines · 38 tokens per session scan A 19a57aae5863

Subscribe to this mod's changes

code-archaeologist is an agent published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,712 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 2026-08-30.

Related

Other agents, from other repositories

hive-builder

Honey hive subagent. Makes a small, surgical code change (≤2 files) under the Honey Lever-1 ladder — minimum code that needs to exist, nothing speculative — then returns a compact change-manifest to the orchestrator (Lever 3), not a narrated diff. Use when the orchestrator has a well-scoped edit and wants the result…

Green-PT/honey-for-devs · 90 tokens

hive-scout

Honey hive subagent. Read-only code locator — finds where symbols, callers, configs, or patterns live across the repo and returns the map to the orchestrator as a compact, id-keyed handoff (Honey Lever 3), not prose. Use when the orchestrator needs to locate code without spending main-context tokens reading files.…

Green-PT/honey-for-devs · 76 tokens

engineer

Implement and test to high quality under the orchestrator-assigned identity. Full subagent.

griddynamics/rosetta · 21 tokens

planner

Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.

griddynamics/rosetta · 23 tokens

t-800-factory-architect

Проектирует спецификацию нового субагента: subagent vs skill vs command vs rule, naming, readonly, model, category, calls/calledBy graph. Use when designing a new agent before any files are written. Readonly design phase only.

Khar-AG/t-800-agent · 60 tokens

t-800-cloud-hub-prompt

Пишет тонкие product-agnostic Hub Instructions (blank) и Client TZ-builder Instructions для Cursor Automations. Use when lead запросил черновики Instructions после capability map. Do NOT use when схема pack/callback; smoke; KB curator; копирование чужого product corpus как шаблон.

Khar-AG/t-800-agent · 70 tokens