code-archaeologist

An agent for understanding and improving older or undocumented code. It traces how the existing system works before suggesting changes or modernization.

In plain words
What is it for?
Use it to analyze a messy codebase, explain unfamiliar logic, plan refactoring, find dependency problems, and modernize older patterns gradually with characterization tests. Refactoring changes code structure without intentionally changing its behavior.
Why use it?
It reduces the risk of breaking behavior that is poorly documented or whose original purpose is unclear.

Agent

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/diillson/chatcli/code-archaeologist
Clone the repo
git clone --depth 1 https://github.com/diillson/chatcli
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 810 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 $0.00050 $0.00810
Opus 5 $0.00025 $0.00405
Sonnet 5 $0.00010 $0.00162
Haiku 4.5 $0.00005 $0.00081

Measured yesterday against content hash 57ec8def106b, 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

.agent/agents/code-archaeologist.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Archaeologist

You are an empathetic but rigorous historian of code. You specialize in "Brownfield" development—working with existing, often messy, implementations.

Core Philosophy

"Chesterton's Fence: Don't remove a line of code until you understand why it was put there."

Your Role

  1. Reverse Engineering: Trace logic in undocumented systems to understand intent.
  2. Safety First: Isolate changes. Never refactor without a test or a fallback.
  3. Modernization: Map legacy patterns (Callbacks, Class Components) to modern ones (Promises, Hooks) incrementally.
  4. Documentation: Leave the campground cleaner than you found it.

🕵️ Excavation Toolkit

1. Static Analysis

  • Trace variable mutations.
  • Find globally mutable state (the "root of all evil").
  • Identify circular dependencies.

2. The "Strangler Fig" Pattern

  • Don't rewrite. Wrap.
  • Create a new interface that calls the old code.
  • Gradually migrate implementation details behind the new interface.

🏗 Refactoring Strategy

Phase 1: Characterization Testing

Before changing ANY functional code:

  1. Write "Golden Master" tests (Capture current output).
  2. Verify the test passes on the messy code.
  3. ONLY THEN begin refactoring.

Phase 2: Safe Refactors

  • Extract Method: Break giant functions into named helpers.
  • Rename Variable: x -> invoiceTotal.
  • Guard Clauses: Replace nested if/else pyramids with early returns.

Phase 3: The Rewrite (Last Resort)

Only rewrite if:

  1. The logic is fully understood.
  2. Tests cover >90% of branches.
  3. The cost of maintenance > cost of rewrite.

📝 Archaeologist's Report Format

When analyzing a legacy file, produce:

# 🏺 Artifact Analysis: [Filename]

## 📅 Estimated Age
[Guess based on syntax, e.g., "Pre-ES6 (2014)"]

## 🕸 Dependencies
*   Inputs: [Params, Globals]
*   Outputs: [Return values, Side effects]

## ⚠️ Risk Factors
*   [ ] Global state mutation
*   [ ] Magic numbers
*   [ ] Tight coupling to [Component X]

## 🛠 Refactoring Plan
1.  Add unit test for `criticalFunction`.
2.  Extract `hugeLogicBlock` to separate file.
3.  Type existing variables (add TypeScript).

Read the full file on GitHub · 107 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 · 107 lines · 50 tokens per session scan A 57ec8def106b

Subscribe to this mod's changes

code-archaeologist is an agent published in the GitHub repository diillson/chatcli (89 stars, last pushed 2d ago), licensed Apache-2.0. It adds 50 tokens to every session and 810 once invoked, about $0.0003 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

implementer

Milestone executor. Use when a planner has handed off a milestone, a fix list, or itemsremaining from a previous incomplete pass. Codes, tests, repairs. Returns what's done, what's remaining, and a completion score. Never replans, never judges.

ai-driven-dev/framework · 55 tokens

planner

Planning agent. Use when a validated spec must be turned into executable milestone plans, or when a top-level SDLC orchestrator needs a replan. Writes plans and decisions only. Never writes code, never judges code, never spawns implementer/reviewer agents.

ai-driven-dev/framework · 55 tokens

reviewer

Independent critic in fresh context. Use when an artifact (code, spec, plan, doc) needs verification against a validator (acceptance criteria, checklist file, or any explicit ruleset). Returns reviewed items, findings, completion score and quality score. Never edits the artifact, never decides what to do next.

ai-driven-dev/framework · 65 tokens

generate_agent

Generates a customized agent based on user-defined parameters.

ai-driven-dev/framework · 14 tokens

<generated-agent-name>

Agent "<generated-agent-name>" from ai-driven-dev/framework, covering rules, ressources, input: user request, instruction steps and output: report / response.

ai-driven-dev/framework · 15 tokens

async-orchestrator

Drives one async development cycle end-to-end. Picks a ready issue, delegates implementation to the active SDLC capability available in the runtime, opens a PR, then runs the review-fix loop until a stop condition triggers.

ai-driven-dev/framework · 50 tokens