All Claude Code modsOG-Matcha/tessera
tessera
One mod for Claude Code, Windows and CJK first: pasted-image and text previews in any terminal, themed replies with CJK-correct tables and charts, long edit diffs folded, unfinished tasks carried into the next session, and guards for multi-agent runs and Traditional Chinese writing
review UI rewrite
tessera reaches L2 (writes or runs) by its classified calls and passed claude plugin validate on Claude Code 2.1.302.
- Events hooked: 9
- API methods referenced: 34
- Access from classified calls: L2, writes or runs: runs processes, sets env vars, changes config, drives Claude, writes the prompt box, reads files, reads env vars, reads settings, reads the transcript, persists state, draws
- Unclassified calls: 3 (
$.prompt.read,$.state.get,$.state.set), full access unknown - Static scan, not a runtime test
Install hint
/plugin install tessera --marketplace OG-Matcha/tesseraFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
L2 Writes or runsother: $.prompt.read, other: $.state.get, other: $.state.set, runs processes, sets env vars, changes config, drives Claude, writes the prompt box, reads files, reads env vars, reads settings, reads the transcript, persists state, drawsValidation
Passed on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Observed events
- Bash calls, PowerShell calls, TaskStop calls, every tool call, Agent calls, Workflow calls, TaskCreate calls, TaskUpdate calls, TodoWrite calls, mcp__tessera__inbox_fixed calls, compaction, every prompt
- Hooks
session.start, session.start {surface=terminal}, ui.render {component=AbovePrompt}, tool.call {tool=Bash}, tool.call {tool=PowerShell}, tool.call {tool=TaskStop}, ui.render {component=AbovePrompt}, turn.complete, turn.start, ui.render {component=AbovePrompt}, tool.call, tool.call {tool=Agent}, tool.call {tool=Workflow}, ui.render {component=Pane, requestId=tessera-setup}, tool.call {tool=TaskCreate}, tool.call {tool=TaskUpdate}, tool.call {tool=TodoWrite}, ui.render {component=AbovePrompt}, session.end, ui.render {component=AbovePrompt}, tool.call {tool=mcp__tessera__inbox_fixed}, session.compact, prompt.submit, command.run {command=tessera}, ui.render {component=ToolResult}, ui.render {component=UserMessage}, ui.render {component=ToolGroup}, ui.render {component=ToolUse}, ui.render {component=TurnDuration}, ui.render {component=CommandOutput}, ui.render {component=AssistantMessage}- API calls
$.clock.every, $.clock.now, $.command.register, $.config.set, $.env.get, $.env.set, $.fs.exists, $.fs.list, $.fs.read, $.fs.stat, $.model.classify, $.process.run, $.prompt.fill, $.prompt.read, $.session.cwd, $.session.id, $.session.messages, $.session.repo, $.session.usage, $.settings.read, $.state.get, $.state.set, $.store.delete, $.store.get, $.store.keys, $.store.set, $.tool.register, $.ui.close, $.ui.copy, $.ui.invalidate, $.ui.open, $.ui.resolve, $.ui.status, $.ui.toast- Validation on 2.1.302
- Passed
- Scanned revision
d6a7e3954c9b- Marketplace passed
- og-matcha
- UI rewrite review
- UI hook source contains control-character strings. Review any values passed to next() as rewritten props.text; the scanner does not trace whether these strings reach that call. hooks/guard.ts:188, hooks/peek.ts:98, hooks/peek.ts:99, hooks/render.tsx:218, hooks/vendor/mermaid-text.js:4, hooks/vendor/prism.js:1
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/OG-Matcha--tessera--tessera/)
[](https://mods.aidojo.si/mods/OG-Matcha--tessera--tessera/)