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 skills/burgebj/claude_everything/everything-claude-codenpx skills add burgebj/claude_everything --skill everything-claude-codegit clone --depth 1 https://github.com/burgebj/claude_everythingWrote 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/burgebj/claude_everything/everything-claude-code)<a href="https://agentmods.dev/skills/burgebj/claude_everything/everything-claude-code"><img src="https://agentmods.dev/badge/skills/burgebj/claude_everything/everything-claude-code.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 | $0.00000 | $0.01351 |
| Opus 5 | $0.00000 | $0.00675 |
| Sonnet 5 | $0.00000 | $0.00270 |
| Haiku 4.5 | $0.00000 | $0.00135 |
Grade A, and why
everything-claude-code 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 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.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
# everything-claude-code Development Patterns
> Auto-generated skill from repository analysis
## Overview
This skill teaches you the core development patterns, coding conventions, and collaborative workflows used in the `everything-claude-code` JavaScript repository. You'll learn how to add or update skills, agents, commands, install targets, and documentation, as well as how to maintain code quality and consistency across the project. The guide is based on real repository analysis and is designed to help contributors onboard quickly and work effectively.
---
## Coding Conventions
**File Naming**
- Use `camelCase` for JavaScript files and directories.
- Example: `installManifests.js`, `installTargets/registry.js`
**Import Style**
- Use relative imports for modules within the project.
```js
// Example
const registry = require('./registry');
Export Style
- Mixed: both CommonJS (
module.exports) and ES6 (export) styles may be present.// CommonJS module.exports = function install() { ... }; // ES6 (if present) export function install() { ... }
Commit Messages
- Use Conventional Commits with prefixes:
fix,feat,docs,chore
- Keep commit messages concise (average ~56 characters).
- Example:
feat: add support for new install target
- Example:
Workflows
Add or Update Skill
Trigger: When introducing or updating a skill for agents
Command: /add-skill
- Create or update
SKILL.mdinskills/<skill-name>/ - Optionally add or update related agent or command files
- Update
manifests/install-modules.jsonto register the skill - Update
AGENTS.mdand/orREADME.mdto reflect the new skill - If documentation is multilingual, update
docs/zh-CN/andREADME.zh-CN.md
Example:
# Add a new skill
mkdir -p skills/myNewSkill
nano skills/myNewSkill/SKILL.md
# Register the skill
nano manifests/install-modules.json
# Update documentation
nano AGENTS.md
nano README.md
Add or Update Agent
Trigger: When introducing or updating an agent definition
Command: /add-agent
- Create or update agent definition in
agents/<agent-name>.mdor.opencode/prompts/agents/ - Update
.opencode/opencode.jsonor similar registry/config - Update
AGENTS.mdto reflect new/changed agents - Optionally update orchestration or skills that reference the agent
Add or Update Command
Trigger: When introducing or improving a workflow command
Command: /add-command
- Create or update command markdown file in
commands/<command-name>.md - If related, update
AGENTS.mdorREADME.mdto document the new command - If command is part of a workflow, update or add related agent/skill files
Add New Install Target or Adapter
Trigger: When supporting a new install environment or integration
Command: /add-install-target
- Create new install scripts and documentation under a dedicated directory (e.g.,
.codebuddy/,.gemini/) - Add or update install target file in
scripts/lib/install-targets/ - Update
manifests/install-modules.jsonandschemas/*.schema.jsonas needed - Update
scripts/lib/install-manifests.jsandscripts/lib/install-targets/registry.js - Add or update related tests in
tests/lib/install-targets.test.js
Dependency Update via Dependabot
Trigger: When Dependabot detects an outdated dependency
Command: /update-dependency
- Update dependency version in
package.json,yarn.lock, or workflow YAML - Regenerate lockfiles if needed
- Commit with a standardized message referencing dependency and version
- Optionally update
.github/dependabot.yml
Hook or CI Script Refactor or Fix
Trigger: When fixing, optimizing, or refactoring hooks or CI scripts
Command: /fix-hook
- Edit
hooks/hooks.jsonand/orscripts/hooks/*.jsor shell scripts - Update or add related test files in
tests/hooks/ortests/scripts/ - If needed, update configuration or schema files
- Optionally update documentation (
WORKING-CONTEXT.md,README.md)
Documentation Update or Sync
Trigger: When updating, clarifying, or synchronizing documentation
Command: /update-docs
- Edit or add markdown files in
docs/,AGENTS.md,README.md,WORKING-CONTEXT.md, etc. - If multilingual, update
docs/zh-CN/andREADME.zh-CN.md - Optionally update related skill or agent documentation
Testing Patterns
- Test Files: Use the pattern
*.test.jsfor test files. - Framework: No specific testing framework detected; use standard Node.js or your preferred test runner.
- Location: Tests are typically placed alongside the code they test or in
tests/subdirectories. - Example:
// tests/lib/install-targets.test.js const assert = require('assert'); const installTarget = require('../../scripts/lib/install-targets/myTarget');
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.
- 4d ago First seen · 168 lines · 0 tokens per session scan A 63d9834de724
everything-claude-code is a skill published in the GitHub repository burgebj/claude_everything (7 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,351 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…