anthony-chaudhary/dos-kernel
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ claude mcp add dos -e PYTHONIOENCODING=YOUR_PYTHONIOENCODING -- dos-mcp $ npx degit anthony-chaudhary/dos-kernel/.claude ./rig-dos-kernel # inspect, then merge into .claude/
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 dos -e PYTHONIOENCODING=YOUR_PYTHONIOENCODING -- dos-mcp $ npx degit anthony-chaudhary/dos-kernel/.claude/skills/issue-verify .claude/skills/issue-verify $ npx degit anthony-chaudhary/dos-kernel/.claude/skills/issue-work .claude/skills/issue-work $ npx degit anthony-chaudhary/dos-kernel/.claude/skills/release .claude/skills/release $ npx degit anthony-chaudhary/dos-kernel/.claude/skills/stable-release .claude/skills/stable-release $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-class-cycle .claude/skills/dos-class-cycle $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-dispatch-loop .claude/skills/dos-dispatch-loop $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-dispatch .claude/skills/dos-dispatch $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-enforce-tune .claude/skills/dos-enforce-tune $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-goal-fleet .claude/skills/dos-goal-fleet $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-goal-gate .claude/skills/dos-goal-gate $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-next-up .claude/skills/dos-next-up $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-plan-price .claude/skills/dos-plan-price $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-promote .claude/skills/dos-promote $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-replan-loop .claude/skills/dos-replan-loop $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-replan .claude/skills/dos-replan $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-self-improve .claude/skills/dos-self-improve $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-setup .claude/skills/dos-setup $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-skillify .claude/skills/dos-skillify $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-stats .claude/skills/dos-stats $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-supervise-loop .claude/skills/dos-supervise-loop $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-unstick .claude/skills/dos-unstick $ npx degit anthony-chaudhary/dos-kernel/claude-plugin/skills/dos-witness-claim .claude/skills/dos-witness-claim
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)
| server | source | est. tokens |
|---|---|---|
| dos-mcp · "dos" env: PYTHONIOENCODING | binary | 2.5k |
Skills (22)
issue-verifyissue-workreleasestable-releasedos-class-cycledos-dispatch-loopdos-dispatchdos-enforce-tunedos-goal-fleetdos-goal-gatedos-next-updos-plan-pricedos-promotedos-replan-loopdos-replandos-self-improvedos-setupdos-skillifydos-statsdos-supervise-loopdos-unstickdos-witness-claim
Hooks (5)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | dos hook session-start --workspace . 2>/dev/null || true |
| Stop | * | dos hook stop --workspace . 2>/dev/null || true |
| Stop | * | dos hook stop-failure --success --workspace . 2>/dev/null || true |
| Stop | * | dos hook live-rotate --workspace . 2>/dev/null || true |
| StopFailure | overloaded|server_error|rate_limit | python scripts/rate_limit_rewake.py --workspace . || true |
Permissions
deny (0)
—
ask (0)
—
allow (2)
Bash(python scripts/trajectory_audit.py:*)
Bash(python scripts/git_hygiene.py:*)
Similar rigs
anthony-chaudhary/fak
Agentic Runtime
Skill Collector 22.8k tok ·
eugene1g/agent-safehouse
Sandbox your local AI agents so they can read/write only what they need
Minimalist 1.5k tok ·
jgravelle/jdocmunch-mcp
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
Pragmatist 18.0k tok ·
movieclaw/MovieClaw
Next-gen AI media server. One container replaces Sonarr, Radarr, Prowlarr, Bazarr, Jellyseerr and Jellyfin, with a web app, a native iPhone app, and an AI agent that gets things done. Free for personal use.
Minimalist 305 tok ·