agentrigs
+ submit rig
~ / rigs / Abhi902 / headroom-plugin

Abhi902/headroom-plugin

Claude Code plugin that keeps big outputs out of your context with the local, offline headroom engine: hcat compress-on-read, an automatic read gate, Dangi nudges, a savings badge in the status line, and a doctor that repairs setup with you

↗ GitHub ★ 11 no license updated 6d ago collection Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.7k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add headroom -e HEADROOM_UPDATE_CHECK=YOUR_HEADROOM_UPDATE_CHECK -e HF_HUB_OFFLINE=YOUR_HF_HUB_OFFLINE -- headroom mcp serve
$ npx degit Abhi902/headroom-plugin/skills ./rig-headroom-plugin/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.

$ claude mcp add headroom -e HEADROOM_UPDATE_CHECK=YOUR_HEADROOM_UPDATE_CHECK -e HF_HUB_OFFLINE=YOUR_HF_HUB_OFFLINE -- headroom mcp serve
$ npx degit Abhi902/headroom-plugin/skills/doctor .claude/skills/doctor
$ npx degit Abhi902/headroom-plugin/skills/headroom-usage-indicator .claude/skills/headroom-usage-indicator

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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
headroom
env: HEADROOM_UPDATE_CHECK, HF_HUB_OFFLINE
 binary 2.5k

Skills (2)

doctorheadroom-usage-indicator

Similar rigs

sravan27/context-os
Cut Claude Code token usage by 40.9% and ship a CI gate for coding-agent cost leaks. Stdlib Python hook + GitHub Action for Claude Code, Codex, Cursor, and agentic coding teams.
★ 10 project Claude Code 3 skills 5mo ago
Pragmatist 680 tok ·
WinterDDo/claude-skill-flywheel
A Claude Code plugin that gives Claude a memory: it remembers your corrections, turns the repeated ones into principles, and invokes the right skill each turn.
★ 2 project Claude Code 3 skills 4mo ago
Minimalist 1.1k tok ·
MTsatsarov/ai-setup
Claude Code marketplace: claude-kit, an interview-driven generator for per-project .claude/ setups
★ 1 setup Claude Code 3 skills 1mo ago
Minimalist 226 tok ·
ArchitektApx/Auth-Guard
Claude Code Plugin that prevents leaking secrets to context or ranscripts
★ 0 project Claude Code 3 skills 2mo ago
Minimalist 239 tok ·
copied ✓