modern-web-guidance-src: Skill for Claude Code

.agents/skills/eval-investigation/SKILL.md

investigating-eval-results is a skill for Claude Code, Codex from GoogleChrome/modern-web-guidance-src. It costs 39 tokens per session (4,746 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for understanding why AI coding agents fail evaluation tests, including differences between guided and unguided runs.

In plain words
What is it for?
Investigating evaluation results, checking agent run paths, fixing task or grader files, and rerunning evaluations.
Why use it?
It helps locate the cause of low pass rates and grader failures instead of guessing from the final score.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Gemini CLI.

This is GoogleChrome/modern-web-guidance-src's own configuration. It tells Claude Code and Codex how to work on modern-web-guidance-src itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything modern-web-guidance-src configures →

About the project

Modern Web Guidance is a source repository for coding-agent skills that provide web-platform guidance, recommended practices, and browser compatibility information. It helps coding agents choose newer web APIs and patterns when generating web applications. The catalogue skills are the guidance produced and maintained by this project.

GoogleChrome/modern-web-guidance-src · 1,022 stars · on GitHub · goo.gle

Reuse

Borrowing it

Nothing to install: this file belongs to GoogleChrome/modern-web-guidance-src. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GoogleChrome/modern-web-guidance-src/main/.agents/skills/eval-investigation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GoogleChrome/modern-web-guidance-src

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for investigating-eval-results

README.md
[![agentmods](https://agentmods.dev/badge/skills/googlechrome/modern-web-guidance-src/eval-investigation/github.svg)](https://agentmods.dev/skills/googlechrome/modern-web-guidance-src/eval-investigation)
Your own site
<a href="https://agentmods.dev/skills/googlechrome/modern-web-guidance-src/eval-investigation"><img src="https://agentmods.dev/badge/skills/googlechrome/modern-web-guidance-src/eval-investigation/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.

agentmods 80×15 button for investigating-eval-results

Your own site · 80×15
<a href="https://agentmods.dev/skills/googlechrome/modern-web-guidance-src/eval-investigation"><img src="https://agentmods.dev/badge/skills/googlechrome/modern-web-guidance-src/eval-investigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,746 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 213
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
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 5.1 $0.00039 $0.04746
Opus 5 $0.00019 $0.02373
Sonnet 5 $0.00008 $0.00949
Haiku 4.5 $0.00004 $0.00475

Measured 9d ago against content hash 2a4908789317, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

investigating-eval-results 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 9d 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.

.agents/skills/eval-investigation/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigating Eval Results

This skill helps you diagnose why AI coding agents are failing evaluations, specifically looking for discrepancies between guided and unguided performance.

Core Philosophy: Immediate Resolution

  • Fix It Now: Do not create tracking issues or delay work. The goal of an investigation is to identify the root cause and implement the fix immediately in the active session.
  • Platform Boundary: When investigating an eval, strictly modify use-case specific files (i.e., task.md, grader.ts, expectations.md, demo apps, and guide.md). Do not attempt to fix bugs in the underlying platform infrastructure or Playwright test environment. If you identify infrastructure issues, note them clearly for the user and suggest filing an issue on GitHub for the engineering team, ensuring the use-case investigation remains focused and clean.
  • Success Rate Goal: The ultimate objective of every investigation is to achieve a 100% Guided Pass Rate. The unguided pass rate does not matter and can be ignored.
  • Autonomous Initiative & Iteration: An investigation is not a single pass. You must autonomously loop through fixing files, re-running evaluations, measuring progress, and rolling back failed attempts until you hit 100% success. Never stop early, and run tests multiple times to ensure your fix is consistently non-flaky.

Communication Protocol

Because evaluation runs (gd eval) take time, check in with the user approximately every 30 seconds to provide a helpful narrative summary of what the agent is currently doing.

Whenever you summarize progress during these check-ins, you MUST:

  1. Include a direct quote or code block of the underlying log lines to substantiate your update.
  2. Provide a clickable markdown link to the specific log file being referenced so the user can click through to see the full contents.

However, NEVER include timestamps in your updates, as they add absolutely zero value to the user.

Example of a good check-in:

The agent has successfully retrieved the reference guidance using the modern web skill:

[Modern Web Log]: {"tool":"get_best_practices"}

Reference: task-log

Read the full file on GitHub · 214 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. 9d ago First seen · 214 lines · 39 tokens per session scan A 2a4908789317

Subscribe to this mod's changes

investigating-eval-results is a skill published in the GitHub repository GoogleChrome/modern-web-guidance-src (1,022 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 4,746 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

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

experimental-code-coverage-local-debugger

Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.

chromium/chromium · 59 tokens

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens