Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add iamcxa/kc-claude-plugins/plugin install e2e-pipelineWrote 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/skills/iamcxa/kc-claude-plugins/e2e-debug)<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/e2e-debug"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/e2e-debug/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/e2e-debug"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/e2e-debug.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00048 | $0.06315 |
| Opus 5.5 | $0.00019 | $0.02526 |
| Sonnet 5.5 | $0.00010 | $0.01263 |
| Haiku 4.5 | $0.00005 | $0.00632 |
Grade A, and why
e2e-debug 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Debug — Inject-Observe-Cleanup Orchestrator
Debug frontend runtime bugs by injecting console.log probes into suspect code, observing their output in a browser, diagnosing root cause, and cleaning up all injections. Runs in main context. Dispatches only one agent: e2e-debug-observe.
Invariant: Phase 4 (Cleanup) MUST execute regardless of any failure in prior phases. Treat every phase after Phase 1 as if wrapped in try/finally where finally = Phase 4.
Invocation
/e2e-debug "<bug description>" # standalone (UC1)
/e2e-debug --url <url> --suspect "<file>" # standalone with hints
/e2e-debug --experiment --inject '[...]' --steps "..." --url <url> # experiment (UC2)
/e2e-debug --continue # next round with previous context
/e2e-debug --cleanup # force cleanup of residual injections
/e2e-debug --cleanup --teardown # cleanup + shutdown observer + delete team
| Arg | Effect |
|---|---|
"<description>" |
Bug description — used for hypothesis formation |
--url <url> |
Target URL for browser observation |
--suspect "<file>" |
File(s) to focus analysis on (comma-separated) |
--experiment |
Experiment mode — skip analysis, injection points pre-specified by caller |
--inject '[...]' |
JSON array of injection specs (experiment mode only) |
--steps "..." |
Reproduction steps as semicolon-separated string (experiment mode only) |
--headed |
Open visible browser — user can see and optionally log in before agent continues |
--headless |
Force headless browser (override Teams mode default) |
--model sonnet|haiku|opus |
Model for observer agent (default: haiku). Observer does browser interaction, not reasoning — haiku is cost-effective. Use --model sonnet for diagnostic-heavy sessions. |
--continue |
Resume from previous round's conclusions |
--cleanup |
Force cleanup — skip all phases, run Phase 4 only |
--no-teams |
Force subagent mode even when Agent Teams is available |
--teardown |
With --cleanup: also shutdown observer teammate and delete team. Ignored without --cleanup. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 547 lines · 48 tokens per session scan A 39da13a101c2
e2e-debug is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 6,315 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.