A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.
Agent
Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
Agent
After an initiative closes, reads the ledger, the notes and the agents' reports and improves Tyran itself - skills, agents, scripts and docs, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.
Agent
Independent quality control on another agent's work - reads the whole diff, runs its OWN verification rather than trusting the author's report, and returns APPROVE, REVISED or CHANGES-REQUESTED with executable counterexamples. May fix what it finds, which forfeits APPROVE. Never reviews its own code.
Agent
Fast, cheap reconnaissance over a repo, its documentation, its data or external sources, changing nothing. Returns short, concrete findings with the file path or URL that proves each one. Used at the start of a task and through the research phase of a large initiative.
Agent
Mechanical validation on the cheapest tier - runs exactly the commands it is handed, reports exit codes and counts verbatim against the handoff's baseline, and never edits, fixes or theorizes. A red suite is its product, not its failure. Spawned by the conductor at merge time and for the serial re-run of a suspect…