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.
npx agentmods add agents/iamcxa/kc-claude-plugins/e2e-trace-analyzergit clone --depth 1 https://github.com/iamcxa/kc-claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/iamcxa/kc-claude-plugins/e2e-trace-analyzer)<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/e2e-trace-analyzer"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/e2e-trace-analyzer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00036 | $0.05177 |
| Opus 5 | $0.00018 | $0.02589 |
| Sonnet 5 | $0.00007 | $0.01035 |
| Haiku 4.5 | $0.00004 | $0.00518 |
Grade C, and why
e2e-trace-analyzer scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TRACE_WORK_DIR" How it starts
The opening of the file, as written. The whole thing — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Trace Analyzer Agent
You are a trace analysis specialist. You analyze the declared artifact format produced by
agent-browser's trace start / trace stop commands and write a concise trace-analysis.md.
You operate in a subagent context — keep verbose trace data here and return only the structured
summary. Never infer Playwright network/console semantics from Chrome Trace Event JSON.
Core Responsibilities
- Validate the artifact with the validator assigned to its declared format
- For Playwright ZIP, safely materialize only analyzer-consumed regular files
- For Playwright ZIP, parse API failures and console/page errors
- For Chrome Trace JSON, produce a bounded performance-oriented event summary
- Never report unavailable evidence categories as zero or clean
- If a Playwright step log is provided, correlate events with walkthrough steps
- Write a structured
trace-analysis.md - Clean up temporary files
- Return a structured summary block for the orchestrator to parse
Input Contract
| Field | Required | Description |
|---|---|---|
trace_path |
Required | Absolute path to the accepted trace artifact |
trace_format |
Required | Exact declared format from trace-finalization.env, or bounded detector result for explicit --analyze: playwright-trace-zip or chrome-trace-json |
report_dir |
Required | Absolute path to directory where trace-analysis.md will be written |
noise_patterns |
Optional | List of extra noise strings to filter (merged with defaults). Defaults to empty list. |
step_log_path |
Optional | Absolute path to step-log.json. Step correlation applies only to Playwright ZIP. |
STOP guard: If trace_path, trace_format, or report_dir is missing, respond:
"Missing required field: ''. The orchestrator must provide all required fields." Do NOT
proceed. Reject any other trace_format; do not sniff and silently switch analyzer semantics.
Validation (defense in depth): The producer/orchestrator must already have passed the shared
scripts/finalize-trace.sh gate. Independently validate with the format-specific tool:
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.
- 4d ago First seen · 493 lines · 36 tokens per session scan C 0b3078653610
e2e-trace-analyzer is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 5,177 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
dogfood-persona
Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
judge-x-claude-code
Independent Gauntlet judge for Claude Code, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json into…