Developer tools decision
Claude Code and Codex Assist - History, Diff Viewer, Chat Manager
A competent technical user can reproduce the core functionality (local indexing, diffs, search, analytics) as a VS Code extension within about a week and low ongoing maintenance, so building is realistic and inexpensive compared with the paid tier.
Visit website↗$4.99/mo
$60/yr
Read off the official pricing page.
$100one-off38 h to build
$0/mo3 h/mo upkeep
On cash alone, building overtakes the subscription at 2 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- Index local assistant history directories, parse sessions, compute per-conversation diffs against repository files, provide searchable session browser and usage/token analytics inside a VS Code sidebar webview.
What it still won’t have
- Polish and cross-editor publishing polish (marketplace listings and discoverability).
- Proprietary UX tweaks, branding, and any paid support channels.
- Edge-case parsing rules for obscure session formats and tested client opt-in community features.
- Lifetime updates and the convenience of a maintained commercial release (auto-updates, refunds handling).
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 2 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a VS Code extension (TypeScript) that indexes local assistant history directories (e.g. ~/.claude/, ~/.codex/), stores parsed sessions in a local SQLite (sql.js) DB, and provides a sidebar webview UI (React) with: searchable session browser, file timeline, GitHub-style diff viewer (side-by-side and inline via a JS diff library), one-click undo/reapply, token usage/cost analytics (input/output/cache breakdown and quota burn-down), session export to Markdown, and session archive/restore. Explicitly out of scope: cloud sync and paid telemetry collection. Include filesystem-watching, robust error handling, unit and integration tests for parsing/indexing/diffing, CI for building VSIX, and installation instructions for VS Code, Cursor, and Open VSX.
How we checked
How the score was reached
- Build verdict base78
- Price verified on pricing page+3
- Evidence score81
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 1
Every page the run actually retrieved.
- official productClaude Code and Codex Assist — official product & pricing
Integrity checks
What held up, and what did not.
