Snapshot
Continue to About ↓- What it does
- WOZCODE is a locally installed plugin that augments Anthropic's Claude Code, replacing Claude Code's built-in search, read, edit and SQL tools with optimized versions intended to cut token usage per turn.
More detail
- The vendor says this makes Claude Code sessions cheaper, faster and higher-performing on coding tasks
- it is not a separate model or a proxy and requires your existing Claude subscription or API key.
- Best for
- Individual Claude Code users and engineering teams who hit session or plan limits or carry material Claude Code token spend, especially those running many parallel sessions or heavy database and codebase exploration work.
More detail
- Buyers who want code and prompts to stay on their own machine and stay out of the vendor's API path.
- Pricing
- Free tier: $0/month, no signup or card, full tool set, but savings capped at $100/month ($200/month with a corporate email)
More detail
- org accounts get a shared $100/seat/month pool up to 5 seats.
- Pro: $20/week per seat, described as unlimited Claude Code savings plus priority support, cancel anytime, with a
- Main limitation
- Anyone not using Claude Code, or expecting a standalone coding agent or model of its own.
More detail
- Also a poor fit for buyers who need certified compliance (SOC 2 is stated as in progress), who need unlimited savings without paying, or who cannot accept local code-execution risk and non-refundable fees.
- Record
- Static profile
- Reviewed
- Evidence
- Public web research
- Machine access
- Structured profile ↗
About
- WOZCODE is a locally installed plugin that augments Anthropic's Claude Code, replacing Claude Code's built-in search, read, edit and SQL tools with optimized versions intended to cut token usage per turn.
- The vendor says this makes Claude Code sessions cheaper, faster and higher-performing on coding tasks
- it is not a separate model or a proxy and requires your existing Claude subscription or API key.
What it helps with
- Long Claude Code sessions re-feed prior context on every tool call, so input tokens and cost compound over a session.
- Exact-match edit failures caused by whitespace and quote differences trigger retry loops that burn tokens and time.
- Developers hit Claude Code session and plan limits during long or highly parallel work.
- Raw shell commands like cat, grep and find produce verbose, unstructured output that consumes context.
- Understanding an unfamiliar database requires many exploratory round-trips before useful answers emerge.
- Prior Claude Code sessions are not easily searchable later, so context has to be rebuilt manually.
Capabilities
A practical view of what is available and where limitations apply.
| Offering | Available | Detail |
|---|---|---|
| Single-call Search tool | Yes | Combines glob, regex and file read with ranked snippets, claimed to cut three calls into one. |
| AST-based read truncation | Yes | Replaces function bodies with stubs while keeping types and exports; vendor claims 40-60% fewer tokens on reads. |
| Batched multi-file Edit | Yes | Accepts an edits array across multiple files in one call; vendor claims fewer calls per change. |
| Fuzzy edit matching | Yes | Levenshtein-tolerant matching for whitespace and curly-quote drift, aimed at fewer retries. |
| SQL tool with schema introspection | Yes | AST-based database introspection, live queries and a foreign-key graph; vendor claims roughly five calls collapse to one. |
| Local savings dashboard and side-by-side benchmark | Yes | /woz-savings and /woz benchmark compare WOZCODE against vanilla Claude Code on your own repo; results are self-measured. |
| Session Recall | Yes | Local semantic search across past sessions, described by the vendor as a new capability. |
| Subagents | Yes | woz:code main agent plus a read-only woz:explore agent using a smaller model, with automatic delegation. |
| SOC 2 certification | Limited | Stated on the official security page as actively in progress, not certified. |
| Independent third-party benchmarks or reviews | Unknown | None were found in the evidence pack; headline performance figures are vendor-reported and internally inconsistent between pages. |
Bot trust
How confidently AI systems can verify this profile from public evidence.
—of 100
ChatGPT—/100
Claude—/100
This profile has not completed a Bot Score assessment yet.
Evidence
Where this record came from, when it was reviewed, and how confidently it can be used.
- Verification
- Scribble researched these facts from the linked public sources.
- The owner has not manually confirmed every field.
- Last reviewed
- Primary source
- wozcode.com
Technical profile details
Record ID
bc4fd91d-7bb4-4e8c-8b08-13b43b8c86eeCanonical URLhttps://profiles.scribble.network/listing/wozcode-bc4fd91d