Open Source · Zero Dependencies · MIT · Live-Tracked Release Version
Latest release version MIT license GitHub stars

Governance infrastructure for
AI-agent teams

System Kit stops your AI coding agents from destroying each other's work. Download the kit, paste one prompt into any agent thread, and get instant multi-thread coordination (four-mutex model with scoped parallel CODE), atomic machine-checked claims, claim/lock task queues, verification gates, push discipline, key isolation, and institutional memory. No technical background needed — setup is one pasted prompt plus plain-English questions, and your agent does all the file work. Works with or without git. Built from real production incidents across 26+ concurrent AI-agent sessions. Plain markdown methodology — works with opencode, Claude Code, Cursor, Codex, and any LLM agent.

⭐ GitHub Repo ↗ Read the Setup Prompt ↗

100% Free & Open Source (MIT). Zero telemetry, zero network calls, zero data collection.

MIT
Open Source License
11
Documented Patterns
12
Failure Classes Documented
4
Mutexes (Scoped CODE)
📜 System Kit Highlights LIVE
One pasted prompt · no technical background
Atomic, machine-checked claims
Four mutexes · scoped parallel CODE
11 patterns, 12 documented failure classes
Works with or without git · any LLM agent
MIT · Markdown · Zero Telemetry

AI Agents Are Productive & Completely Ungoverned

Run two agents in parallel without a system and these failures are not hypothetical — every rule in System Kit exists because one of them actually happened:

💥

Two agents edit the same files

Lost work and broken builds from unchecked parallel edits.

👻

Invented APIs

Agents confidently call functions that don't exist anywhere in your codebase.

🚫

Untested syntax errors ship

Dead pages reach production because nothing forced a local verify.

🌀

Context compaction mid-task

The same problem gets researched twice because nothing was checkpointed.

📉

Cumulative data shown as daily

Users catch reporting bugs before you do.

☠️

Dead models eat your requests

Quotas burn on routing errors no one probed for.

🔑

Keys read into chat context

Secrets leak to external servers through agent transcripts.

Four Steps to Governed Agent Sessions

STEP 1 · DOWNLOAD
📂

Download the kit

Green Code button on GitHub → Download ZIP, then unzip it anywhere. No terminal, no install.

STEP 2 · PASTE
📋

Paste SETUP_PROMPT.md into your agent

Open opencode, Claude Code, Cursor, or any agent in your project — paste the prompt as your first message.

STEP 3 · ANSWER
💬

Answer plain-English questions

The agent scans your project, asks about it in plain English, then builds everything: it auto-detects what your environment supports (shell? git? CI?), copies the kit's docs/ folder in, installs the atomic-claim and scope-check scripts, and fills every file. Already have docs/? Governance gets a dedicated subfolder.

STEP 4 · DONE

Governance is live

Task board, thread registry, build log, checkpoints, laws. Every future thread starts at docs/START_HERE.md.

Nine Capabilities, Zero Runtime Dependencies

CONCURRENCY
🔒

Four-Mutex Model

CODE (scoped — parallel holders with disjoint scopes, including glob scopes like src/**/*.test.ts), LEDGER, DB-CF, and MERGE lock separately — docs threads never wait behind code threads, and merge-backs are serialized.

TASK QUEUE
📋

Claim / Lock / Release

Single entry point, priority queue, and conflict detection so every thread knows exactly which task is safely its own.

ENFORCEMENT
⚛️

Atomic, Machine-Checked Claims

A shared-lock register script makes claims race-free — two threads racing for one task, exactly one wins. Overlapping scopes are refused at claim time and rejected at commit time (git projects). Stale threads auto-flag at 2h+ without a heartbeat.

VERIFICATION

Verification Gates

Local-first testing discipline with a five-step order — owner verifies last, never first.

MEMORY
🧠

Institutional Memory

Append-only ledgers plus a checkpoint/resume system mean context loss never costs re-research.

PUSH DISCIPLINE
🚦

Owner-Gated Deploys

Ledger currency is required before pushing; deployments stay owner-gated, always.

SECURITY
🛡️

Machine-Checked Security

Credentials are handled internally and never exposed to agent contexts or logs — and a CI security scan now enforces it: credential patterns, prompt-injection markers, and untracked secret stores are flagged file:line, with matched values never echoed.

DEPLOYMENT
🌐

Universal Deployment

Same system in a plain folder with no git, a git repo, or hosted with CI — capabilities are auto-detected at setup with zero extra questions.

OWNER GATE
🗣️

Plain-Language Decisions

Decisions arrive in simple English — the owner is interrupted only when genuinely needed.

Release History Lives on GitHub

📋

Every release, documented as it ships

The live badge above always shows the current release — no stale version numbers here. Full history, from the initial release through every added pattern, fix, and breaking change, is maintained in the repository's changelog.

Read CHANGELOG.md ↗

Machine-Checked Where It Counts. Not Magic.

Claims are atomic and race-free wherever a POSIX shell exists, and (in git projects) commits outside a thread's declared scope are rejected by hook. But machine enforcement covers claims and commits — it is not runtime surveillance. Where no shell exists, the kit degrades to a fully documented manual protocol: correct behavior stays explicit, checkable, and recoverable, just not automatic. Known constraints: filesystem locking assumes one shared filesystem, and templates are English-only. We think honesty about this beats pretending otherwise.

Stop losing work to ungoverned agents

Star the repo, download the kit, paste the setup prompt. Governance live in under five minutes.

⭐ View System Kit on GitHub ↗