gg2762/Claude-Code-Skill-Architecture-and-Token-Management
The non-obvious setup that keeps a Claude Code project sharp as it grows: skill architecture, context budget, document ingestion, and permission/trust. The things I wish I knew before I started.
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit gg2762/Claude-Code-Skill-Architecture-and-Token-Management/skills ./rig-claude-code-skill-architecture-and-token-management/skills MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit gg2762/Claude-Code-Skill-Architecture-and-Token-Management/skills/context-budget .claude/skills/context-budget $ npx degit gg2762/Claude-Code-Skill-Architecture-and-Token-Management/skills/ingestion-compression .claude/skills/ingestion-compression $ npx degit gg2762/Claude-Code-Skill-Architecture-and-Token-Management/skills/permission-setup .claude/skills/permission-setup $ npx degit gg2762/Claude-Code-Skill-Architecture-and-Token-Management/skills/skill-architecture .claude/skills/skill-architecture
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (4)
Similar rigs
IFAKA/claude-code-dotfiles
Shareable Claude Code context optimization config — curl install
Minimalist 498 tok ·
cveralyon/axel-setup
AXEL — Claude Code team configuration package. Additive bootstrap with hooks, agents, commands, skills, and plugins.
Pragmatist 4.0k tok ·
ngc-shj/claude-code-config
Safe default settings for Claude Code with agentic multi-model architecture
Fort Knox 1.9k tok ·
AndrewDongminYoo/cc-agents-kit
Claude Code plugin marketplace. guard-hooks: five defensive hooks that block dangerous shell commands and secrets access, catch the two zsh quoting mistakes that fail silently, and warn on lockfile drift and shellcheck findings.
Skill Collector 2.4k tok ·