FeHelper is a browser extension that combines tools for web development, testing, data conversion, debugging, and everyday productivity in one toolbox. It is used by developers, testers, operations staff, and other browser users for tasks such as formatting JSON, testing WebSockets, beautifying code, capturing pages, and generating test data. The catalogue entries provide rules, a skill, and an instruction for using or extending the extension.
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 instructions/zxlie/fehelper/agents-mdgit clone --depth 1 https://github.com/zxlie/FeHelperWrote 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/instructions/zxlie/fehelper/agents-md)<a href="https://agentmods.dev/instructions/zxlie/fehelper/agents-md"><img src="https://agentmods.dev/badge/instructions/zxlie/fehelper/agents-md.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 5.1 | $0.00480 | $0.00480 |
| Opus 5 | $0.00240 | $0.00240 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
FeHelper AGENTS.md 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 today.
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 — 19 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md instructions for /Users/uncle/github/FeHelper
UI Taste Gate
- For any FeHelper extension UI, popup, options page, devtools surface, website, landing page, or other Web UI implementation/redesign, use the project-local
design-taste-frontendskill first. - Skill path:
.agents/skills/design-taste-frontend/SKILL.md. - Treat
design-taste-frontend/taste-skillas the default quality gate for FeHelper product tone. Any future code change that affects visible UI, interaction polish, layout density, or cross-tool consistency should explicitly apply this skill before editing. - Treat this skill as the aesthetic decision gate: infer the design read, set the variance/motion/density dials, then choose the design system or visual language before editing UI code.
- Apply the skill pragmatically for FeHelper: preserve browser extension constraints, accessibility, performance, bundle size, and existing repo conventions ahead of decorative motion or unnecessary dependencies.
- Before finishing UI work, run the relevant build/lint/tests and use browser or screenshot QA when the changed surface can be exercised locally.
Chrome Extension Context
- Treat every FeHelper
apps/*tool page, popup, options page, devtools page, and content-script surface as part of a Chrome extension, not as a generic standalone website. - Before changing a tool page, identify the tool's actual user job, entry path, runtime APIs, permissions, asset-loading path, and whether it runs as
chrome-extension://, injected content script, popup, options page, or devtools UI. - Preserve extension constraints while coding: Chrome extension CSP,
chrome.runtimeAPIs, packaged relative assets, offline/local execution, bundle size, browser compatibility, and permissions boundaries. - Validation should match the surface. For extension pages, prefer
npm run buildplus loading/testing the built unpacked extension output in Chrome, or an extension-equivalent browser QA path. A plain localhost/static-server run is useful for fast layout checks only and should not be the only proof when Chrome extension APIs, asset paths, permissions, or CSP matter. - When a test uses stubs for
chrome.*APIs, state that it is a supplemental local harness and still verify the affected extension behavior in the corresponding extension context when the change depends on those APIs.
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.
- today First seen · 19 lines · 480 tokens per session scan A a7009ebc8faa
FeHelper AGENTS.md is an instructions file published in the GitHub repository zxlie/FeHelper (5,662 stars, last pushed 2d ago), licensed MIT. It adds 480 tokens to every session, about $0.0024 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 2026-09-04.
Other instructions, from other repositories
chat-on-steroids CLAUDE.md
Claude Code instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
AI-MarkDone copilot-instructions.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai copy enhance - ai coding agent instructions, project overview, architecture patterns, adapter pattern for multi-platform support and shadow dom isolation.
AI-MarkDone AGENTS.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai-markdone engineering guide, project facts, read order, common commands and non-negotiables.
aegisloop AGENTS.md
AGENTS.md instructions for MHW888888/aegisloop, covering aegisloop development rules, scope, safety, verification and publishing.
agent-inbox AGENTS.md
Instructions for OGZamasu/agent-inbox, covering connecting an agent, claude code, chatgpt — custom gpt with actions, mcp clients and anything else.
multi-ai-panel AGENTS.md
AGENTS.md instructions for xiaojiou176-open/multi-ai-panel, covering agents, public surface rules, current visibility truth, protected paths and no-code-loss and destructive action discipline.