jjanczur/tyran
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'
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit jjanczur/tyran/agents ./rig-tyran/agents $ npx degit jjanczur/tyran/skills ./rig-tyran/skills $ npx degit jjanczur/tyran/hooks ./rig-tyran/hooks
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.
$ npx degit jjanczur/tyran/skills/browser-check .claude/skills/browser-check $ npx degit jjanczur/tyran/skills/code-review .claude/skills/code-review $ npx degit jjanczur/tyran/skills/deslop .claude/skills/deslop $ npx degit jjanczur/tyran/skills/doctor .claude/skills/doctor $ npx degit jjanczur/tyran/skills/fidelity-gate .claude/skills/fidelity-gate $ npx degit jjanczur/tyran/skills/hello .claude/skills/hello $ npx degit jjanczur/tyran/skills/pr-feedback .claude/skills/pr-feedback $ npx degit jjanczur/tyran/skills/prompt-tuning .claude/skills/prompt-tuning $ npx degit jjanczur/tyran/skills/retro .claude/skills/retro $ npx degit jjanczur/tyran/skills/root-cause .claude/skills/root-cause $ npx degit jjanczur/tyran/skills/run .claude/skills/run $ npx degit jjanczur/tyran/skills/setup .claude/skills/setup $ npx degit jjanczur/tyran/skills/skill-writing .claude/skills/skill-writing $ npx degit jjanczur/tyran/skills/status .claude/skills/status
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/jjanczur/tyran/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/retro.md https://raw.githubusercontent.com/jjanczur/tyran/main/agents/retro.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/jjanczur/tyran/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/jjanczur/tyran/main/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/jjanczur/tyran/main/agents/verifier.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:
{
"permissions": {
"deny": [
"Read(~/.ssh/**)",
"Read(**/.env)",
"Bash(rm -rf *)",
"Read(./.env)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(**/*.pem)",
"Bash(rm -rf /*)",
"Read(~/.aws/**)",
"Bash(rm -rf:*)",
"Read(.env)",
"Bash(git push --force*)",
"Read(**/*.key)",
"Read(./.env.*)",
"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(wget *)",
"Bash(npm publish:*)",
"Bash(gh pr merge *)",
"Bash(chown *)",
"Bash(docker *)"
]
}
} Skills (14)
browser-checkcode-reviewdeslopdoctorfidelity-gatehellopr-feedbackprompt-tuningretroroot-causerunsetupskill-writingstatus
Subagents (5)
| implementer | 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 sh |
| retro | 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 overfit |
| reviewer | 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 e |
| scout | 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 |
| verifier | 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 s |
Similar rigs
tammai/ai-sdlc
Claude Code plugin for vibe coding on the AI-native SDLC playbook: intent → design → spec → plan → verify → review → ship. Runs on a Claude subscription, with opinionated stacks (Nuxt/Next + Cloudflare, Go + Postgres, Flutter, Tauri) and de
Orchestrator 3.2k tok ·
leavemagic-cyber/earned-confidence
A behavior contract for AI coding agents — every rule added after a real failure. Ships with a verifier agent that cannot edit what it judges.
Pragmatist 3.6k tok ·
Saba-Var/claude-ward
A read-only tripwire that watches Claude Code's local config and reports suspicious changes.
Pragmatist 1.8k tok ·
PedroMosquera/squadai
One config. Every AI agent. Zero drift. Idempotent setup for OpenCode, Claude Code, Cursor, Windsurf, and Copilot.
Fort Knox 2.7k tok ·