KushalP1/context-doctor
See where your AI agent's tokens go and stop paying for the ones that do nothing. Local CLI, MCP server, hook and proxy for Claude Code, Claude Desktop, Cursor, Codex, Gemini CLI and Anthropic/OpenAI/Gemini API apps. No API key, no telemetr
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit KushalP1/context-doctor/skills ./rig-context-doctor/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 KushalP1/context-doctor/plugin/skills/autopilot .claude/skills/autopilot $ npx degit KushalP1/context-doctor/plugin/skills/checkup .claude/skills/checkup $ npx degit KushalP1/context-doctor/plugin/skills/compact-window .claude/skills/compact-window $ npx degit KushalP1/context-doctor/plugin/skills/fix .claude/skills/fix $ npx degit KushalP1/context-doctor/plugin/skills/overhead .claude/skills/overhead $ npx degit KushalP1/context-doctor/plugin/skills/pack .claude/skills/pack $ npx degit KushalP1/context-doctor/plugin/skills/savings .claude/skills/savings $ npx degit KushalP1/context-doctor/plugin/skills/spend .claude/skills/spend $ npx degit KushalP1/context-doctor/skills/context-doctor .claude/skills/context-doctor
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (9)
Similar rigs
RoninForge/budgetclaw
Local spend monitor for Claude Code with hard budget caps: track cost per project and git branch, get phone alerts, and stop a runaway agent before the bill lands. Zero keys, zero prompts, zero latency. roninforge.org/budgetclaw
Minimalist 1.7k tok · · Q5
mocartlex-wq/cognitive-core
Self-hosted Docker stack for cross-platform AI agent rooms (Claude Code + ChatGPT + any LLM). MIT.
Automator 3.5k tok · · Q15
Thanatos9404/llmslim
Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
Pragmatist 2.6k tok · · Q0
nnguyenquangg/harness-engineering-kit
The public part of a harness engineering setup for Claude Code: spec-first workflow, three parallel AI reviewers, UI walkthroughs verified through the real API, draft PRs with evidence, and a layered harness template.
Skill Collector 1.3k tok · · Q0