CodeClone

Deterministic Structural Change Controller for AI-assisted Python development

Let agents move fast.

Keep structural change explicit, bounded, and verifiable.

[][pypi-link] [][pypi-link] [][pypi-link] [][license-link] [][discord-link]

[][tests-link] [][benchmark-link]

---

[!IMPORTANT]

Sections marked `2.1 alpha` require the

CodeClone 2.1 prerelease.

Everything else works with the current stable release,

CodeClone 2.0.2.

What is CodeClone?

CodeClone helps developers use AI coding agents without losing control of structural change.

Before an agent edits code, CodeClone records the intended change, maps the structural blast radius, and establishes explicit edit boundaries. After the edit, it compares the real patch with the declared scope, verifies structural regressions, and leaves an auditable review receipt.

CodeClone does not generate or rewrite source files, and it does not ask an LLM to decide whether a structural change is safe. Every finding and every gate comes from deterministic repository facts shared across agents, human reviewers, IDEs, reports, and CI.

CodeClone requires no hosted service or cloud account. Analysis state, controller state, Engineering Memory, and trajectories are stored locally.

Why intent comes before the diff

Most review tools begin after the patch already exists. CodeClone begins earlier:

task request

→ declared intent → structural blast radius → explicit boundary → actual patch → deterministic verification

Agent scope expansion can look reasonable in the final diff. A narrow task may quietly spread into shared helpers, tests, configuration, public APIs, or unrelated modules.

By the time that expansion reaches the final diff, it already looks intentional. CodeClone catches it at the declared boundary instead — by comparing what the agent said it would change with what it actually changed.

Quick start

Requires Python 3.10 or newer.

1. Analyze a repository

Run the stable release without installing anything:

uvx codeclone@latest .

Prefer a browsable report? Generate the HTML view and open it:

uvx codeclone@latest . --html --open-html-report

Once you use it regularly, install it as a local tool:

uv tool install codeclone

codeclone .

2. Record the current structural baseline

Before asking an agent to change the repository, capture the accepted state once:

codeclone . --update-baseline

git add codeclone.baseline.json git commit -m "chore: add CodeClone structural baseline"

The baseline records the structural debt that already exists. Future analysis can then separate new regressions from findings that were already present, so agents and reviewers can focus on what the current change introduced.

Updating the baseline is an explicit governance action. Do not regenerate it merely to make a failing check pass.

3. Connect your AI agent — 2.1 alpha

Continue to Agent change control below to install the MCP control surface and wire CodeClone into Claude Code, Cursor, VS Code, Codex, or Claude Desktop.

One canonical structural report

CodeClone runs one deterministic analysis and renders the same canonical report through every supported surface.

The report covers:

• function, block, and segment clones;
• clone drift and duplicated branch families;
• complexity, coupling, cohesion, dependency cycles, and dead code;
• Module Map — a package/module dependency graph with cycle, hub, overloaded-module, and unwind-candidate views;
• Guided Finding Review — a prioritized review queue with shared finding cards, filters, and progress tracking;
• public API inventory and baseline-aware API break detection;
• external coverage joined with structural hotspots;
• deterministic structural health and review priorities.

codeclone . --json --html --md --sarif --text

How CodeClone works · Canonical report contract

Baseline-aware governance and CI

The baseline is a versioned, integrity-checked contract that records the accepted structural state of the repository.

It lets CodeClone and connected agents distinguish:

• findings that already existed;
• regressions introduced by the current change;
• deliberate baseline updates approved by the user.

Check future changes against the committed baseline:

codeclone . --ci

Use CodeClone in GitHub Actions:

- uses: orenlab/codeclone/.github/actions/codeclone@v2

with: fail-on-new: "true" sarif: "true" pr-comment: "true"

CI can reject newly introduced clones, metric regressions, API breaks, and coverage regressions without requiring the existing repository to be clean first.

Baseline contract · CI integration and quality gates

How CodeClone differs

Linters check style and correctness file by file. Clone detectors report duplication and stop there. Hosted review bots ask a model for an opinion about a finished diff.

CodeClone combines CFG-based clone detection, multi-metric baseline governance, and a read-only MCP control surface in one local-first, open-source package — and applies them before the edit happens, not only after. Structural facts are computed deterministically, so the same input always produces the same verdict, in the terminal, in CI, and inside your agent's loop.

Agent change control — 2.1 alpha

Install the MCP control surface

uv tool install --prerelease allow "codeclone[mcp]"

codeclone-mcp --transport stdio

The server exposes 38 MCP tools covering analysis, change control, blast radius, memory, and diagnostics. Responses are built for agent loops: deterministic next_tool guidance, token-budget-aware payloads, and replies that keep mandatory control facts inline while linking full evidence for drill-down.

Before gating agents or CI, confirm [tool.codeclone] and local gitignore hygiene:

codeclone setup status

codeclone setup plan codeclone setup apply # or: codeclone setup wizard

See Repository setup and readiness.

Wire it into your client

Every client uses the same MCP interface and the same canonical structural facts.

The controlled-change workflow

For an agent, the normal workflow is:

analyze → start → edit → finish

Analyze. CodeClone builds one canonical structural report for the repository and compares it with the accepted baseline.

Start. start_controlled_change:

• records the agent's intent;
• maps structural blast radius;
• separates editable paths from review context and do-not-touch boundaries;
• exposes the regression budget relative to the accepted baseline;
• returns the authoritative edit_allowed result.

Edit. The agent writes the code. CodeClone does not generate or rewrite source files. Where the host supports hooks, integrations can stop edits unless edit_allowed=true. While editing, the agent stays oriented through Live Implementation Context instead of rediscovering the repository with broad searches.

Finish. finish_controlled_change:

• resolves the actual changed files;
• checks declared scope against the real patch;
• verifies structural changes;
• validates optional review claims;
• records Patch Trail evidence;
• produces an auditable review receipt.

If the patch crosses the declared boundary or introduces regressions beyond the budget, verification fails — and the receipt records exactly where and why. The result is not an AI opinion about the patch. It is a deterministic comparison between declared intent, repository structure, the accepted baseline, and the actual change.

Read the Structural Change Controller guide

Live Implementation Context

get_implementation_context serves the agent bounded, task-scoped context directly from the current analysis run:

• struct