tool-renderer

A guide for adding support for new Claude Code tools in a transcript viewer, an interface that displays an agent's conversation and tool activity. It covers parsing tool data and turning it into HTML.

In plain words
What is it for?
Use it to add rendering for tools such as web search or web fetching, define their data models, parse transcript entries, and format their results.
Why use it?
It provides a clear path through the different code parts involved in displaying a tool. It also helps developers use the richer structured result data when it is available.

Skill for Claude CodeCodex

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 skills/daaain/claude-code-log/tool-renderer
Any agent
npx skills add daaain/claude-code-log --skill tool-renderer
Clone the repo
git clone --depth 1 https://github.com/daaain/claude-code-log

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,271 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 $0.00041 $0.03271
Opus 5 $0.00020 $0.01636
Sonnet 5 $0.00008 $0.00654
Haiku 4.5 $0.00004 $0.00327

Measured 2d ago against content hash 9db1e17182e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool-renderer 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 2d ago.

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.

.claude/skills/tool-renderer/SKILL.md · 441 lines

How it starts

The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementing a Tool Renderer

This guide walks through adding rendering support for a new Claude Code tool, using WebSearch as an example.

Before You Start

Examine existing test data to understand the tool's actual JSON structure:

# Find test files containing the tool
rg -l "ToolName" test/test_data/

# Look at actual JSONL entries
rg '"name":\s*"ToolName"' test/test_data/ -A 2 -B 2

Key fields to identify:

  • Input parameters: What's in tool_use.input?
  • toolUseResult structure: What metadata does the structured result contain?
  • tool_result.content: What does the raw text output look like?

The toolUseResult field on transcript entries often contains richer structured data than tool_result.content. Always prefer parsing from toolUseResult when available.

Overview

Tool rendering involves several components working together:

  1. Models (models.py) - Type definitions for tool inputs and outputs
  2. Factory (factories/tool_factory.py) - Parsing raw JSON into typed models
  3. HTML Formatters (html/tool_formatters.py) - HTML rendering functions
  4. Renderers - Integration with HTML and Markdown renderers

Step 1: Define Models

Tool Input Model

Add a Pydantic model for the tool's input parameters in models.py:

class WebSearchInput(BaseModel):
    """Input parameters for the WebSearch tool."""
    query: str

Tool Output Model

Add a dataclass for the parsed output. Output models are dataclasses (not Pydantic) since they're created by our parsers, not from JSON:

@dataclass
class WebSearchLink:
    """Single search result link."""
    title: str
    url: str

@dataclass
class WebSearchOutput:
    """Parsed WebSearch tool output."""
    query: str
    links: list[WebSearchLink]
    preamble: Optional[str] = None  # Text before the Links
    summary: Optional[str] = None   # Markdown analysis after the Links

Note: Some tools have structured output with multiple sections. WebSearch is parsed as preamble/links/summary - text before Links, the Links JSON array, and markdown analysis after. This allows flexible rendering while preserving all content.

Read the full file on GitHub · 441 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. 2d ago First seen · 441 lines · 41 tokens per session scan A 9db1e17182e5

Subscribe to this mod's changes

tool-renderer is a skill published in the GitHub repository daaain/claude-code-log (1,201 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 3,271 once invoked, about $0.0002 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens