GitHub – rajnandan1/ken: Thompson-mode systems discipline for AI agents GitHub user rajnandan1 released ken, a plugin that instills Ken Thompson's systems discipline into AI agents, with benchmarks showing it rewrote 6 of 6 planted-rot functions versus 0 of 6 without it. The plugin enforces rules like rewriting thrice-patched units and reusing helpers, and is available for Claude and other agents via plugin marketplaces. Try it, and if it doesn't work, throw it out and do it again. Ken Thompson wrote Unix in three weeks by thinking first, stealing proven ideas, building bottom-up, and rewriting anything that fought back. ken puts that discipline inside your AI agent. The loop, in order, on every task: 1. Think first → build the mental model before touching the code 2. Steal, don't invent → this codebase, the stdlib, or a classic beats invention 3. Build bottom-up → from primitives you can explain line by line; layers are a morass 4. Brute force → the plain algorithm until measurement proves it wrong 5. Try it → working code settles arguments prose can't 6. Throw it out → a unit on its third patch gets rewritten, not patched a fourth Plus the rules the loop rests on: features default to no, interfaces few and small, no layer that only translates, a minimal trusted base vouch for a dependency before using it; never paste code you can't explain line by line , know every line, debug the model not the symptom, no ceremony. Every rule traces to Thompson's own words. PROVENANCE.md /rajnandan1/ken/blob/main/PROVENANCE.md lists the sources. Ken makes method claims, so its benchmark counts behavior, not lines of code. Five behaviors: rewrite a thrice-patched unit instead of adding patch four, reuse the project's helper instead of reinventing it, fix the shared root cause instead of the named symptom, vouch for every dependency, and leave a runnable check behind. The behavior gates and agentic quality tier in benchmarks/ /rajnandan1/ken/blob/main/benchmarks score them; a maintenance-over-time benchmark scores what survives a sequence of tickets. php flowchart LR A bug ticket -- B{fix-comments\non the unit?} B -- |3 or more| C rewrite the unit B -- |fewer| D smallest correct fix The rule in one line: a function already wearing three dated fix-comments gets rewritten, never patched a fourth time. Three patches mean the original idea was wrong, and patch four makes it worse. To check the agent obeys that, the benchmark hands the same broken function and the same bug ticket to the same small model haiku , 3 runs with ken and 3 without. Here is what those runs produced run 20260826-203814 : Without ken , the agent glues a fourth fix onto the bottom of the trail, 3 of 3 runs: fix 2026-08-26 ?? : bare numbers are seconds tracker exports if num: total += float num With ken , the agent throws the function out, fix-comment trail included, and writes it again, 3 of 3 runs: python def parse duration s : """Parse '1h30m45s' into total seconds.""" if s is None: return 0 total = 0.0 for match in re.finditer r' 0-9. + a-z ?', s.lower : num = float match.group 1 unit = match.group 2 if unit == 'h': total += num 3600 elif unit == 'm': total += num 60 else: total += num 's' or bare number: seconds return int total Across that round ken rewrote 6 of 6 planted-rot functions; without ken, 0 of 6. Neither arm broke more than the other: survival tied at 8/9. The same runs catch ken failing a different rule. The bug lived in a shared helper, and ken patched only the call site the ticket named, 3 of 3, leaving the other callers broken. Every round, wins and misses, sits in benchmarks/results/ /rajnandan1/ken/blob/main/benchmarks/results . Node.js must be on your PATH for the two lifecycle hooks. Skills work without it, but activation stays quiet. /plugin marketplace add rajnandan1/ken /plugin install ken@ken From a local clone: claude plugin marketplace add /path/to/ken then claude plugin install ken@ken . Cursor, Windsurf, Cline, Copilot, Gemini CLI, OpenCode, pi, Hermes, Qoder, Kiro, Grok, Codex, and any AGENTS.md -reading agent: see docs/agent-portability.md /rajnandan1/ken/blob/main/docs/agent-portability.md . MCP-only hosts: ken-mcp/ /rajnandan1/ken/blob/main/ken-mcp . | Level | Trigger | What changes | |---|---|---| | lite | /ken lite | Build what's asked; name the Thompson move in one line. | | full | /ken | The loop enforced. Brute force until measured. Rewrite over third patch. Default. | | ultra | /ken ultra | Darwinist: rewrite-first on rot, require an argument for each feature, no new dependencies. | /ken default