cdeust/zetetic-team-subagents
One epistemic standard on three hosts. Claude Code: 15 problem-shaped skills, 97 sourced reasoning patterns, 120 agents, commit-time gates. Codex and Gemini CLI: portable evidence-synthesis, design and goal-loop skills. Shared gates block u
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 cdeust/zetetic-team-subagents/agents ./rig-zetetic-team-subagents/agents $ npx degit cdeust/zetetic-team-subagents/commands ./rig-zetetic-team-subagents/commands $ npx degit cdeust/zetetic-team-subagents/skills ./rig-zetetic-team-subagents/skills $ npx degit cdeust/zetetic-team-subagents/hooks ./rig-zetetic-team-subagents/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 cdeust/zetetic-team-subagents/plugins/zetetic-design/skills/design .claude/skills/design $ npx degit cdeust/zetetic-team-subagents/plugins/zetetic-loop/skills/advisor-model .claude/skills/advisor-model $ npx degit cdeust/zetetic-team-subagents/plugins/zetetic-loop/skills/goal .claude/skills/goal $ npx degit cdeust/zetetic-team-subagents/plugins/zetetic-loop/skills/plan .claude/skills/plan $ npx degit cdeust/zetetic-team-subagents/plugins/zetetic-loop/skills/refine-goal .claude/skills/refine-goal $ npx degit cdeust/zetetic-team-subagents/plugins/zetetic-loop/skills/verify-goal .claude/skills/verify-goal $ npx degit cdeust/zetetic-team-subagents/plugins/zetetic-reasoning/skills/evidence-synthesis .claude/skills/evidence-synthesis $ npx degit cdeust/zetetic-team-subagents/skills/boundary-design .claude/skills/boundary-design $ npx degit cdeust/zetetic-team-subagents/skills/causal-audit .claude/skills/causal-audit $ npx degit cdeust/zetetic-team-subagents/skills/decision-bias-check .claude/skills/decision-bias-check $ npx degit cdeust/zetetic-team-subagents/skills/estimation .claude/skills/estimation $ npx degit cdeust/zetetic-team-subagents/skills/experience-and-transmission .claude/skills/experience-and-transmission $ npx degit cdeust/zetetic-team-subagents/skills/failure-forensics .claude/skills/failure-forensics $ npx degit cdeust/zetetic-team-subagents/skills/formal-correctness .claude/skills/formal-correctness $ npx degit cdeust/zetetic-team-subagents/skills/measurement-discipline .claude/skills/measurement-discipline $ npx degit cdeust/zetetic-team-subagents/skills/narrative-sensemaking .claude/skills/narrative-sensemaking $ npx degit cdeust/zetetic-team-subagents/skills/normative-design .claude/skills/normative-design $ npx degit cdeust/zetetic-team-subagents/skills/problem-reframing .claude/skills/problem-reframing $ npx degit cdeust/zetetic-team-subagents/skills/representation-and-possibility .claude/skills/representation-and-possibility $ npx degit cdeust/zetetic-team-subagents/skills/structure-discovery .claude/skills/structure-discovery $ npx degit cdeust/zetetic-team-subagents/skills/systems-leverage .claude/skills/systems-leverage
$ curl -fsSL --create-dirs -o .claude/agents/advisor.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/advisor.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/data-scientist.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/data-scientist.md $ curl -fsSL --create-dirs -o .claude/agents/dba.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/dba.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/engineer.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/engineer.md $ curl -fsSL --create-dirs -o .claude/agents/experiment-runner.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/experiment-runner.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/alexander.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/alexander.md $ curl -fsSL --create-dirs -o .claude/agents/alkhwarizmi.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/alkhwarizmi.md $ curl -fsSL --create-dirs -o .claude/agents/altshuller.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/altshuller.md $ curl -fsSL --create-dirs -o .claude/agents/archimedes.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/archimedes.md $ curl -fsSL --create-dirs -o .claude/agents/arendt.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/arendt.md $ curl -fsSL --create-dirs -o .claude/agents/aristotle.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/aristotle.md $ curl -fsSL --create-dirs -o .claude/agents/bateson.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/bateson.md $ curl -fsSL --create-dirs -o .claude/agents/beer.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/beer.md $ curl -fsSL --create-dirs -o .claude/agents/borges.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/borges.md $ curl -fsSL --create-dirs -o .claude/agents/boyd.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/boyd.md $ curl -fsSL --create-dirs -o .claude/agents/braudel.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/braudel.md $ curl -fsSL --create-dirs -o .claude/agents/bruner.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/bruner.md $ curl -fsSL --create-dirs -o .claude/agents/carnot.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/carnot.md $ curl -fsSL --create-dirs -o .claude/agents/champollion.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/champollion.md $ curl -fsSL --create-dirs -o .claude/agents/coase.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/coase.md $ curl -fsSL --create-dirs -o .claude/agents/cochrane.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/cochrane.md $ curl -fsSL --create-dirs -o .claude/agents/curie.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/curie.md $ curl -fsSL --create-dirs -o .claude/agents/darwin.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/darwin.md $ curl -fsSL --create-dirs -o .claude/agents/deming.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/deming.md $ curl -fsSL --create-dirs -o .claude/agents/dijkstra.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/dijkstra.md $ curl -fsSL --create-dirs -o .claude/agents/eco.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/eco.md $ curl -fsSL --create-dirs -o .claude/agents/einstein.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/einstein.md $ curl -fsSL --create-dirs -o .claude/agents/ekman.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/ekman.md $ curl -fsSL --create-dirs -o .claude/agents/engelbart.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/engelbart.md $ curl -fsSL --create-dirs -o .claude/agents/erdos.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/erdos.md $ curl -fsSL --create-dirs -o .claude/agents/erlang.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/erlang.md $ curl -fsSL --create-dirs -o .claude/agents/euler.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/euler.md $ curl -fsSL --create-dirs -o .claude/agents/feinstein.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/feinstein.md $ curl -fsSL --create-dirs -o .claude/agents/fermi.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/fermi.md $ curl -fsSL --create-dirs -o .claude/agents/feynman.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/feynman.md $ curl -fsSL --create-dirs -o .claude/agents/fisher.md https://raw.githubusercontent.com/cdeust/zetetic-team-subagents/main/agents/genius/fisher.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"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(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| memory env: MEMORY_AGENT_ID | local / custom | 2.5k |
Skills (21)
designadvisor-modelgoalplanrefine-goalverify-goalevidence-synthesisboundary-designcausal-auditdecision-bias-checkestimationexperience-and-transmissionfailure-forensicsformal-correctnessmeasurement-disciplinenarrative-sensemakingnormative-designproblem-reframingrepresentation-and-possibilitystructure-discoverysystems-leverage
Subagents (79)
| advisor model: fable | Frontier-model consultant for the Advisor loop — reviews plans at decision points and verifies completion while a cheaper model executes |
| architect model: opus | Proactively analyze structural changes, decomposition decisions |
| code-reviewer model: sonnet | Proactively review code changes for Clean Architecture, SOLID, size limits |
| data-scientist model: sonnet | Data scientist specializing in profile-first EDA, distribution-aware modeling, missingness classification |
| dba model: sonnet | Database specialist adapting to any engine (PostgreSQL, MySQL, SQLite, MongoDB, etc.) — schema design |
| devops-engineer model: sonnet | DevOps engineer specializing in CI/CD, containerization, infrastructure-as-code, observability |
| engineer model: sonnet | Software engineer specializing in Clean Architecture, SOLID, and root-cause problem solving |
| experiment-runner model: sonnet | ML/empirical experiment design specialist — pre-registration, Fisher-style design, reproducibility manifests |
| frontend-engineer model: sonnet | Frontend engineer specializing in component-driven UI, state ownership, accessibility |
| alexander model: opus | Christopher Alexander reasoning pattern — pattern languages for design knowledge |
| alkhwarizmi model: opus | Al-Khwarizmi reasoning pattern — reduce a messy, irregular problem to canonical form, enumerate all cases exhaustively, then apply the known solution mechanically, when ad hoc special-casing keeps gro |
| altshuller model: opus | Genrich Altshuller reasoning pattern — systematic invention through contradiction resolution |
| archimedes model: opus | Archimedes reasoning pattern — heuristic-then-proof two-stage discovery: find the result by any means (physical intuition, analogy, simulation), then prove it rigorously by an independent method |
| arendt model: opus | Hannah Arendt reasoning pattern — thoughtlessness audit for systemic failures caused by suppressed judgment, checking the labor/work/action classification before attributing harm to malice |
| aristotle model: opus | Aristotle reasoning pattern — four-causes interrogation for complete causal explanation |
| bateson model: opus | Gregory Bateson reasoning pattern — diagnose pathological interaction patterns (schismogenesis, double binds, meta-communication conflicts) between components rather than blaming either party, when an |
| beer model: opus | Stafford Beer reasoning pattern — viable system diagnosis, variety engineering, recursive viability. |
| borges model: opus | Jorge Luis Borges reasoning pattern — exhaustive-space audit, map-territory discipline |
| boyd model: opus | John Boyd reasoning pattern — cycle Observe-Orient-Decide-Act faster than the adversary, treating orientation as the decisive phase, to win adversarial or competitive decision cycles |
| braudel model: opus | Fernand Braudel reasoning pattern — three-timescale decomposition of phenomena into structure (longue duree) |
| bruner model: opus | Jerome Bruner reasoning pattern — recognize when narrative (not paradigmatic/causal) reasoning is the right mode, and analyze story structure, canonical breach, and identity-construction, when the que |
| carnot model: opus | Sadi Carnot reasoning pattern — deriving theoretical efficiency limits for any process |
| champollion model: opus | Jean-François Champollion reasoning pattern |
| coase model: opus | Ronald Coase reasoning pattern — transaction cost analysis for drawing system/organizational boundaries |
| cochrane model: opus | Cochrane/Glass reasoning pattern — systematic evidence synthesis across multiple independent studies |
| curie model: opus | Proactively establish measurement discipline when a quantity is claimed, an anomaly appears |
| darwin model: opus | Charles Darwin reasoning pattern — long-horizon patient observation, systematic collection of variation |
| deming model: opus | W. Edwards Deming reasoning pattern — classify variation as common-cause (redesign the system) or special-cause (find the event) before reacting, run PDSA with an explicit prediction, and drive out fe |
| dijkstra model: opus | Proactively enforce correctness discipline when \"it works in tests\" is not an acceptable standard |
| eco model: opus | Umberto Eco reasoning pattern — Model Reader/User construction for designing interpretable artifacts, classifying them as open or closed, and diagnosing shared sign-system conventions that broke down |
| einstein model: opus | Albert Einstein reasoning pattern — gedankenexperiment (ride the phenomenon in your mind) |
| ekman model: opus | Paul Ekman reasoning pattern — anchor subjective experience to observable anatomical units |
| engelbart model: opus | Douglas Engelbart reasoning pattern — augment human capability rather than automate it away |
| erdos model: opus | Paul Erdős reasoning pattern — the probabilistic method (prove existence by showing a random construction succeeds with positive probability), find phase-transition thresholds, and establish extremal |
| erlang model: opus | Agner Krarup Erlang reasoning pattern — queuing theory for capacity planning |
| euler model: opus | Leonhard Euler reasoning pattern — notation design as infrastructure that makes solutions visible, through exhaustive enumeration, aggressive abstraction, and productive generalization |
| feinstein model: opus | Feinstein/Sackett reasoning pattern — systematic clinical reasoning through differential diagnosis |
| fermi model: opus | Fermi reasoning pattern — order-of-magnitude estimation as a first move, bracket before solve |
| feynman model: opus | Proactively audit integrity of claims, procedures, and results — rederive from scratch, explain to a freshman |
| fisher model: opus | Ronald A. Fisher reasoning pattern — design the experiment before running it: randomize to eliminate confounds, block to cut variance, replicate for power, and use factorial designs, so a causal claim |
Slash commands (29)
/_index/agent/list/agent/spawn/agent/status/design/genius/compose/genius/invoke/genius/route/git/clean/git/commit/git/pr/quality/pre-commit/quality/pre-push/research/notebook/research/session/session/memory-audit/session/memory-sync/session/recall/session/save/skill/run/zetetic/advisor-loop/zetetic/difficulty/zetetic/engineering-loop/zetetic/estimate/zetetic/goal-loop/zetetic/integrity/zetetic/provenance/zetetic/review/zetetic/verify
Similar rigs
VersoXBT/claude-initial-setup
75 skills, 14 agents, 15 commands for Claude Code. Plug-and-play starter kit covering TypeScript, Python, Go, Rust, React, Next.js, FastAPI, Django, Docker, CI/CD, security, testing, and more. Cross-AI support for Cursor, Copilot, and Codex
Orchestrator 5.1k tok ·
theishandubey/claude-config
A complete Claude Code setup. An agent roster, an orchestration playbook, safe defaults and curated skills, installed with one command.
Orchestrator 4.0k tok ·
anujg21/claude-engineering-os
A repository template that gives Claude Code a working engineering method: phased workflow, path-scoped standards, independent review agents, and hooks that block dangerous commands.
Skill Collector 3.1k tok ·
damilola-elegbede-org/claude-config
Configurations Files for Claude
YOLO Cowboy 35.2k tok ·