tailscale-p2p-governance-not-clone
Skill29 starsChanged 7 months agoMITView on GitHub
Tailscale PAM and HiveMind (2026-09) are decentralized sync & Zero-Trust network formats, not ThumbGate clones. Steal the P2P G-Set CRDT rule sync and PAM privileged execution diode onto existing ThumbGate PreToolUse rails; never vendor HiveMind, require root SSH, or expose public broker endpoints. Slash: /tailscale-p2p-governance-not-clone.
Files
Tailscale P2P Governance — compare, do not clone
Goal
Provide zero-trust, peer-to-peer synchronization of agent prevention rules, thumbs feedback, and privileged action diodes across multi-machine development swarms over a private Tailnet — without external cloud dependencies or centralized coordinator bottlenecks.
Constraints
| NEVER | ALWAYS |
Clone HiveMind (projectmentor/hive-mind) | Map P2P sync onto ThumbGate's G-Set CRDT prevention rules |
| Depend on external cloud servers for agent memory sync | Keep rule sync peer-to-peer over private Tailnet (WireGuard) |
| Require root SSH access or passwordless sudo across nodes | Enforce local PreToolUse diodes on each node independently |
| Transmit raw un-redacted secret blobs across the mesh | Enforce secret-deny redaction before any P2P sync |
| Allow unauthenticated peers to inject prevention rules | Verify Tailscale node identity & cryptographic receipts |
| Claim 100% cloud elimination without local doctor proof | Run node scripts/tailscale-p2p-doctor.js --json |
HARD fail closed. REFUSE unverified sync brokers.
Architectural Steal
- FORMAT Steal from HiveMind:
- Append-only journal.
- G-Set CRDT (monotonically growing set of prevention rules).
- Local-first, decentralized replication over private Tailnet.
- FORMAT Steal from Tailscale PAM:
- Network layer (Tailscale PAM): controls host-to-host and infrastructure access.
- Execution layer (ThumbGate PreToolUse): controls agent command/tool invocation before execution.
Verification & Usage
# Verify local Tailscale P2P governance status
node scripts/tailscale-p2p-doctor.js --json
# Run unit tests
npm test -- tests/tailscale-p2p-adapter.test.jsReferences
- Tailscale September 2026 Newsletter (
tailscale.pdf) adapters/tailscale/TAILSCALE.mdscripts/tailscale-p2p-doctor.js- https://tailscale.com/community/community-projects
In this repository98 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .well-known/llms.txtllms.txt
- activesaddler-curriculum-honestySkill
- article-syndication-pipelineSkill
- autonomous-execution-mandateSkill
- aws-strands-harness-not-cloneSkill
- bolt-forge-opt-in-not-cloneSkill
- ci-gha-buildkite-patterns-not-cloneSkill
- cobble-hot-store-compare-not-cloneSkill
- colab-compute-honesty-not-cloneSkill
- comet-session-loggerSkill
- craft-playbook-gateSkill
- cyberstrike-compare-not-cloneSkill
- datadog-llm-obs-compare-not-cloneSkill
- decisive-step-evaluatorSkill
- deeppattern-discipline-honesty-not-cloneSkill
- earnie-third-author-governanceSkill
- embeddinggemma-multimodal-firewallSkill
- fiddler-control-plane-honestySkill
- gitlab-sandbox-allowlist-not-trustSkill
- graphifySkill
- halo-trace-optimize-not-cloneSkill
- harness-evolution-ceilingSkill
- ideabrowser-connectorSkill
- infoq-architect-honesty-not-cloneSkill
- jit-harness-compare-not-cloneSkill
- meko-datapack-honesty-not-cloneSkill
- mintlify-knowledge-honesty-not-cloneSkill
- model-distress-governanceSkill
- multi-harness-rl-invariantsSkill
- nvidia-specdecode-al-doctorSkill
- omp-coordination-honesty-not-cloneSkill
- openui-catalog-compose-honestySkill
- package-manager-honesty-doctorSkill
- qwenwork-policy-group-honesty-not-cloneSkill
- saas-moat-honesty-not-cloneSkill
- salt-code-policy-honesty-not-cloneSkill
- show-meSkill
- siren-mcp-governanceSkill
- skool-headless-readerSkill
- snapchat-abm-playbook-stealSkill
- strands-harness-sentinelSkill
- thumbgate-board-loopSkill
- thumbgate-daily-discoveriesSkill
- thumbgateSkill
- token-shunt-honesty-not-cloneSkill
- typesafe-typed-questions-not-cloneSkill
- vs-coverage-gap-not-cloneSkill
- vulnerability-pre-action-diodeSkill
- windbg-evidence-diagnosticsSkill
- wisdom-context-artifact-not-cloneSkill
- zero-outbound-spend-they-pay-usSkill
- zvec-grep-compare-not-cloneSkill
- ci-failure-triageSkill
- evidence-first-answerSkill
- fleet-coordinationSkill
- paranoid-mode-honesty-not-cloneSkill
- revenue-truthSkill
- scope-disciplineSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

