Eval Harness
affaan-m/ECC
Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, grade with code-based, model-based, rule, or human graders, and track pass@k…
A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Never use eval() or unsafe dynamic code execution.
MITAuto-check passed
Install Avoid Eval
$ npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install thedaviddias/Front-End-Checklist avoid-eval --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/thedaviddias/Front-End-Checklist.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/avoid-eval .claude/skills/avoid-eval && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "avoid-eval" agent skill from https://github.com/thedaviddias/Front-End-Checklist/tree/main/skills/avoid-eval into .claude/skills/avoid-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "avoid-eval", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/thedaviddias/Front-End-Checklist/tree/main/skills/avoid-evalType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install thedaviddias/Front-End-Checklist avoid-eval --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thedaviddias/Front-End-Checklist.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/avoid-eval .agents/skills/avoid-eval && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "avoid-eval" agent skill from https://github.com/thedaviddias/Front-End-Checklist/tree/main/skills/avoid-eval into .agents/skills/avoid-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "avoid-eval", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install thedaviddias/Front-End-Checklist avoid-eval --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thedaviddias/Front-End-Checklist.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/avoid-eval .cursor/skills/avoid-eval && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "avoid-eval" agent skill from https://github.com/thedaviddias/Front-End-Checklist/tree/main/skills/avoid-eval into .cursor/skills/avoid-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "avoid-eval", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/thedaviddias/Front-End-Checklist.git --path skills/avoid-eval--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install thedaviddias/Front-End-Checklist avoid-eval --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thedaviddias/Front-End-Checklist.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/avoid-eval .gemini/skills/avoid-eval && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "avoid-eval" agent skill from https://github.com/thedaviddias/Front-End-Checklist/tree/main/skills/avoid-eval into .gemini/skills/avoid-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "avoid-eval", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install thedaviddias/Front-End-Checklist avoid-evalInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/thedaviddias/Front-End-Checklist.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/avoid-eval .github/skills/avoid-eval && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "avoid-eval" agent skill from https://github.com/thedaviddias/Front-End-Checklist/tree/main/skills/avoid-eval into .github/skills/avoid-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "avoid-eval", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install thedaviddias/Front-End-Checklist avoid-eval --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thedaviddias/Front-End-Checklist.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/avoid-eval .opencode/skills/avoid-eval && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "avoid-eval" agent skill from https://github.com/thedaviddias/Front-End-Checklist/tree/main/skills/avoid-eval into .opencode/skills/avoid-eval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "avoid-eval", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
avoid-eval- GitHub stars
- 74k
- Token cost
- ~554 tokens
- SKILL.md length
- 243 words
- Files
- 2 (incl. references)
- Skills in repo
- 390
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Never use eval() or unsafe dynamic code execution.
- Reviewing scripts
- SKILL.md covers Quick Reference, Check, Fix and Explain, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Client components
What it does
Avoid Eval is an agent skill from thedaviddias/Front-End-Checklist. Use when reviewing scripts, client components, bundles, or runtime behavior related to Never use eval() or unsafe dynamic code execution. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.
Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/rule.md`).
The repository describes itself as: 🗂 The essential checklist for modern web development, for humans and AI agents. The licence is MIT.
When your agent uses it
- Reviewing scripts
- Client components
- Runtime behavior related to Never use eval()
- Unsafe dynamic code execution
Example prompts
- “/avoid-eval”
What it can do on your machine
Read from SKILL.md and the folder at commit e8d14d0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
frontendchecklist.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Avoid Eval loads about 554 tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 243 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from thedaviddias/Front-End-Checklist at commit e8d14d0, republished under its MIT licence (© thedaviddias). 243 words, ~554 tokens.
Download SKILL.mdSave it as
.claude/skills/avoid-eval/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- avoid-eval
- description
- Use when reviewing scripts, client components, bundles, or runtime behavior related to Never use eval() or unsafe dynamic code execution. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.
- metadata.category
- javascript
- metadata.priority
- critical
- metadata.difficulty
- beginner
- metadata.estimatedTime
- 10
- metadata.source
- frontendchecklist.io
- metadata.url
- https://frontendchecklist.io/rules/javascript/avoid-eval
Never use eval() or unsafe dynamic code execution
eval() and its equivalents are the root cause of some of the most severe XSS vulnerabilities. If any user-controlled string reaches eval(), an attacker can execute arbitrary JavaScript in your users' browsers — stealing sessions, making requests as the user, or redirecting to malicious sites. Content Security Policy (CSP) blocks eval() but not new Function(), and there is never a legitimate use case that can't be solved without it.
Quick Reference
- eval() executes arbitrary strings as code — any user input passed to it is a critical security hole
- new Function() is equally dangerous and not caught by CSP eval restrictions
- setTimeout('code', delay) and setInterval('code', delay) also evaluate strings — use function references instead
- Use JSON.parse() instead of eval() for parsing JSON
Check
Search this codebase for any use of eval(), new Function(), or setTimeout/setInterval with string arguments.
Fix
Replace eval() calls with safe alternatives: JSON.parse for data, object lookups for dynamic dispatch, and Function references for timers.
Explain
Explain why eval() is dangerous, how it enables XSS attacks, and what safe alternatives exist for each use case.
Code Review
Review scripts, client components, and browser execution paths related to Never use eval() or unsafe dynamic code execution. Flag exact imports, event handlers, runtime side effects, or blocking operations that violate the rule, and state how the change should be verified in the browser.
For full implementation details, code examples, and framework-specific guidance,
see references/rule.md.
Rule page: https://frontendchecklist.io/rules/javascript/avoid-eval
© thedaviddias, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in skills/avoid-eval of thedaviddias/Front-End-Checklist.
- SKILL.md
- references/rule.md
Open the folder on GitHubat commit e8d14d0
Compare with similar skills
Avoid Eval next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Avoid Eval this skillthedaviddias/Front-End-Checklist | 74k | — | ~554 | Automated safety check: Pass | MIT | |
| Eval Harnessaffaan-m/ECC | 274k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Evalalirezarezvani/claude-skills | 28k | 1 repos | ~618 | Automated safety check: Pass | MIT | |
| Eval Harnessaffaan-m/ECC | 274k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Eval-Driven Development Harnessaffaan-m/ECC | 274k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Triage Support Bundlenetdata/netdata | 81k | — | ~2.7k | Automated safety check: Pass | GPL-3.0 |
Similar skills
Eval
alirezarezvani/claude-skills
Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
Eval Harness
affaan-m/ECC
Eval-driven development (EDD) ilkelerini uygulayan Claude Code oturumları için formal değerlendirme çerçevesi
Eval-Driven Development Harness
affaan-m/ECC
Sets up eval-driven development for Claude Code workflows: capability and regression evals, three grader types and pass@k reliability metrics.
Triage Support Bundle
netdata/netdata
Investigate a Netdata support bundle offline - the archive netdata-support-bundle produces - to explain one host's alerts, missing data, collector failures, crashes, high CPU or memory, streaming…
Nrepl Eval
penpot/penpot
Evaluate Clojure code via nREPL using the standalone scripts/nrepl-eval.mjs CLI tool.
More from thedaviddias/Front-End-Checklist
All 390 skills in this repoContent Dates Audit
thedaviddias/Front-End-Checklist
Audits article and blog pages for visible publish dates, Article JSON-LD with datePublished and dateModified, and Open Graph time tags, then fixes what is missing.
FAQPage Schema Markup
thedaviddias/Front-End-Checklist
Adds, checks and fixes FAQPage JSON-LD on pages with visible question-and-answer sections so it matches what readers see and can qualify for rich results.
Favicon Audit and Setup
thedaviddias/Front-End-Checklist
Checks that a site's favicon is linked, reachable and large enough for Google search results, and sets up ICO, SVG and Apple touch icon files when they are missing.
Content Freshness Signals
thedaviddias/Front-End-Checklist
Audits article pages for freshness signals, covering the Last-Modified header, Article JSON-LD dateModified and a visible last-updated date, and fixes mismatches.
Geo Meta Tags Audit
thedaviddias/Front-End-Checklist
Audits and fixes geo.region, geo.placename and geo.position meta tags on regional pages, noting where they help (Bing) and where they do not (Google).
Improve a Front-End Checklist Rule
thedaviddias/Front-End-Checklist
Scores and rewrites a Front-End Checklist rule MDX file against a scored quality rubric, replacing generic stub prompts with specific, actionable ones.
Questions about Avoid Eval
What does Avoid Eval do?
A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Never use eval() or unsafe dynamic code execution. Avoid Eval is an agent skill from thedaviddias/Front-End-Checklist. Use when reviewing scripts, client components, bundles, or runtime behavior related to Never use eval() or unsafe dynamic code execution.
When should I use Avoid Eval?
Avoid Eval fits situations like: reviewing scripts; client components; runtime behavior related to Never use eval(); unsafe dynamic code execution.
How do I install Avoid Eval in Claude Code?
Run `npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a claude-code`. Or copy the skill folder (skills/avoid-eval in thedaviddias/Front-End-Checklist) into .claude/skills/avoid-eval in your project. Claude Code loads it when a task matches its description.
How do I install Avoid Eval in Codex?
Run `npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a codex`. Or copy the skill folder (skills/avoid-eval in thedaviddias/Front-End-Checklist) into .agents/skills/avoid-eval in your project. Codex loads it when a task matches its description.
Can I use Avoid Eval in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add thedaviddias/Front-End-Checklist --skill avoid-eval -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/avoid-eval, .gemini/skills/avoid-eval, .github/skills/avoid-eval and .opencode/skills/avoid-eval in your project.
What does Avoid Eval need to run?
SKILL.md names no scripts, command-line tools or credentials: Avoid Eval is instructions for the agent only.
Does Avoid Eval access the network?
SKILL.md names 1 domain. As links in the text: frontendchecklist.io. This is read from the text; nothing was executed.
Is Avoid Eval safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Avoid Eval use?
Avoid Eval is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Avoid Eval use?
About 554 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.
What are the alternatives to Avoid Eval?
Skills that share tags, products or a category with Avoid Eval: Eval Harness (affaan-m/ECC, 274k stars), Eval (alirezarezvani/claude-skills, 28k stars), Eval Harness (affaan-m/ECC, 274k stars) and Eval-Driven Development Harness (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Avoid Eval?
thedaviddias (a GitHub user) maintains it in thedaviddias/Front-End-Checklist, which has 74,388 GitHub stars. The repository holds 390 skills in this directory. The repository was last updated on October 6, 2026.
Source: thedaviddias/Front-End-Checklist on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.