~ / rigs / rajib2k5 / claude-staff-kit

rajib2k5/claude-staff-kit

Staff-level engineering standards for Claude Code: skills, model-routed agents, commands, rules, contexts, and a destructive-ops guard. Installs as a plugin or as ~/.claude dotfiles.

↗ GitHub ★ 0 MIT updated today collection Claude Code Claude plugin
stack: JavaScript
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~6.1k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit rajib2k5/claude-staff-kit/agents ./rig-claude-staff-kit/agents
$ npx degit rajib2k5/claude-staff-kit/commands ./rig-claude-staff-kit/commands
$ npx degit rajib2k5/claude-staff-kit/skills ./rig-claude-staff-kit/skills
$ npx degit rajib2k5/claude-staff-kit/hooks ./rig-claude-staff-kit/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 rajib2k5/claude-staff-kit/skills/claude-agent-orchestration .claude/skills/claude-agent-orchestration
$ npx degit rajib2k5/claude-staff-kit/skills/claude-api-ops .claude/skills/claude-api-ops
$ npx degit rajib2k5/claude-staff-kit/skills/claude-code-config .claude/skills/claude-code-config
$ npx degit rajib2k5/claude-staff-kit/skills/claude-context-management .claude/skills/claude-context-management
$ npx degit rajib2k5/claude-staff-kit/skills/claude-evals .claude/skills/claude-evals
$ npx degit rajib2k5/claude-staff-kit/skills/claude-governance .claude/skills/claude-governance
$ npx degit rajib2k5/claude-staff-kit/skills/claude-prompt-engineering .claude/skills/claude-prompt-engineering
$ npx degit rajib2k5/claude-staff-kit/skills/claude-rag-and-citations .claude/skills/claude-rag-and-citations
$ npx degit rajib2k5/claude-staff-kit/skills/claude-solution-design .claude/skills/claude-solution-design
$ npx degit rajib2k5/claude-staff-kit/skills/claude-tool-and-mcp-design .claude/skills/claude-tool-and-mcp-design
$ npx degit rajib2k5/claude-staff-kit/skills/cost-conscious-orchestration .claude/skills/cost-conscious-orchestration
$ npx degit rajib2k5/claude-staff-kit/skills/data-cost .claude/skills/data-cost
$ npx degit rajib2k5/claude-staff-kit/skills/data-dbt-audit .claude/skills/data-dbt-audit
$ npx degit rajib2k5/claude-staff-kit/skills/data-metric .claude/skills/data-metric
$ npx degit rajib2k5/claude-staff-kit/skills/data-model .claude/skills/data-model
$ npx degit rajib2k5/claude-staff-kit/skills/data-pipeline-debug .claude/skills/data-pipeline-debug
$ npx degit rajib2k5/claude-staff-kit/skills/data-quality .claude/skills/data-quality
$ npx degit rajib2k5/claude-staff-kit/skills/data-snowflake-audit .claude/skills/data-snowflake-audit
$ npx degit rajib2k5/claude-staff-kit/skills/data-snowflake-tune .claude/skills/data-snowflake-tune
$ npx degit rajib2k5/claude-staff-kit/skills/destructive-ops-guard .claude/skills/destructive-ops-guard
$ npx degit rajib2k5/claude-staff-kit/skills/evidence-gated-validation .claude/skills/evidence-gated-validation
$ npx degit rajib2k5/claude-staff-kit/skills/learn-as-you-build .claude/skills/learn-as-you-build
$ npx degit rajib2k5/claude-staff-kit/skills/simple-english .claude/skills/simple-english
$ npx degit rajib2k5/claude-staff-kit/skills/snowflake-sql .claude/skills/snowflake-sql
$ npx degit rajib2k5/claude-staff-kit/skills/staff-adr .claude/skills/staff-adr
$ npx degit rajib2k5/claude-staff-kit/skills/staff-bootstrap .claude/skills/staff-bootstrap
$ npx degit rajib2k5/claude-staff-kit/skills/staff-debug .claude/skills/staff-debug
$ npx degit rajib2k5/claude-staff-kit/skills/staff-design .claude/skills/staff-design
$ npx degit rajib2k5/claude-staff-kit/skills/staff-incident .claude/skills/staff-incident
$ npx degit rajib2k5/claude-staff-kit/skills/staff-migrate .claude/skills/staff-migrate
$ npx degit rajib2k5/claude-staff-kit/skills/staff-onboard .claude/skills/staff-onboard
$ npx degit rajib2k5/claude-staff-kit/skills/staff-perf .claude/skills/staff-perf
$ npx degit rajib2k5/claude-staff-kit/skills/staff-review .claude/skills/staff-review
$ npx degit rajib2k5/claude-staff-kit/skills/staff-security .claude/skills/staff-security
$ npx degit rajib2k5/claude-staff-kit/skills/staff-ship .claude/skills/staff-ship
$ npx degit rajib2k5/claude-staff-kit/skills/staff-tdd .claude/skills/staff-tdd
$ npx degit rajib2k5/claude-staff-kit/skills/staff-validate .claude/skills/staff-validate
$ npx degit rajib2k5/claude-staff-kit/third-party/plugins/cert-safari-quiz/skills/safari .claude/skills/safari
$ npx degit rajib2k5/claude-staff-kit/third-party/plugins/evolv-taste-pilot/skills/frontend-ship-gate .claude/skills/frontend-ship-gate
$ npx degit rajib2k5/claude-staff-kit/third-party/plugins/threejs/skills/threejs-animation-system .claude/skills/threejs-animation-system
$ curl -fsSL --create-dirs -o .claude/agents/adversarial-reviewer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/adversarial-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/analytics-engineer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/analytics-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/codebase-explorer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/codebase-explorer.md
$ curl -fsSL --create-dirs -o .claude/agents/cost-optimizer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/cost-optimizer.md
$ curl -fsSL --create-dirs -o .claude/agents/data-quality-auditor.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/data-quality-auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/dbt-engineer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/dbt-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/dependency-auditor.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/dependency-auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/docs-writer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/docs-writer.md
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/incident-responder.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/incident-responder.md
$ curl -fsSL --create-dirs -o .claude/agents/migration-planner.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/migration-planner.md
$ curl -fsSL --create-dirs -o .claude/agents/performance-engineer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/performance-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/pipeline-debugger.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/pipeline-debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/principal-code-reviewer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/principal-code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/release-manager.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/release-manager.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/researcher.md
$ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/security-auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/snowflake-architect.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/snowflake-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/sre-reliability.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/sre-reliability.md
$ curl -fsSL --create-dirs -o .claude/agents/staff-engineer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/staff-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-engineer.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/test-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/rajib2k5/claude-staff-kit/main/agents/verifier.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

Skills (51)

Subagents (23)

adversarial-reviewer
model: opus
Attacks completed work to find what is wrong with it. Use when the validation router routes the adversarial method (rows 6–9, 12 when T2+ or concurrency/retries/timezone/currency, 13; row-5 procedure
analytics-engineer
model: opus
Owns metric definitions and the semantic layer — makes sure a business term means one thing everywhere, defines metrics with grain and filters explicit, and traces a reported number back to its source
architect
model: opus
Handles complex work where the approach is not yet settled — design with real trade-offs, debugging a cause nobody has identified, concurrency, and anything touching safety, compliance, data deletion,
codebase-explorer
model: sonnet
Read-only reconnaissance across a codebase — locate symbols, map call sites, inventory files matching a pattern, list which tests cover a function, trace an import graph. Use for broad fan-out searche
cost-optimizer
model: opus
Finds and quantifies cloud and warehouse spend reduction — unit economics, idle and over-provisioned resources, data scanned, egress, and commitment options. Use for any spend investigation or savings
data-quality-auditor
model: opus
Audits datasets and pipelines for the silent failures — grain violations, join fan-out, freshness gaps, reconciliation drift, absence-vs-zero errors, and untested keys. Use when a number looks wrong,
dbt-engineer
model: opus
Builds and audits dbt projects — layering, model design, tests, contracts, incremental strategies, macros, and slim CI. Use for any dbt model work, or when a dbt project needs its layering and increme
dependency-auditor
model: sonnet
Inventories dependencies and reports versions, licences, known CVEs, unpinned or unlocked entries, and unused or duplicated packages. Mechanical inventory work, runs on Sonnet. Escalate judgement call
docs-writer
model: sonnet
Drafts READMEs, runbooks, ADRs, design docs, and dbt/model documentation from material you provide. Use when the decisions are already made and the task is writing them down accurately. Drafting from
implementer
model: sonnet
Carries out well-specified changes of simple to moderate difficulty — mechanical edits, wiring something up, writing tests for behaviour already decided, doc updates, refactors with a known shape. Use
incident-responder
model: opus
Drives a live incident — mitigate first, diagnose second — then produces a blameless postmortem with detection-time analysis and owned action items. Use during an active outage or immediately after on
migration-planner
model: opus
Plans schema, data, and API migrations using expand/contract — with a backfill strategy, a real rollback plan, and a dry run at production scale. Use before any migration, backfill, or breaking interf
performance-engineer
model: opus
Diagnoses and fixes performance problems from a measurement, never from intuition — profiling, N+1 and query plans, tail latency, concurrency, caching, and complexity budgets. Use when something is sl
pipeline-debugger
model: opus
Root-causes data pipeline failures across dbt, Airflow, Snowflake tasks/streams, and ingestion — including the hard case where the pipeline reports success but the data is wrong or stale. Use for any
principal-code-reviewer
model: opus
Deep code review for correctness, security, data integrity, and silent failure — the defects tests do not catch. Use before merging non-trivial changes or when you want a diff attacked rather than app
release-manager
model: sonnet
Assembles a release — verifies CI status, collects the changelog from commits, checks version bumps and migration ordering, and confirms the rollback path is stated. Mechanical assembly and checking a
researcher
model: opus
Investigates questions that need sources — library and model comparisons, prior art, standards and regulation, how other projects solved something. Use before adopting a dependency or committing to an
security-auditor
model: opus
Threat-models and audits code for injection, broken authorization, secret exposure, supply-chain risk, crypto misuse, and prompt injection. Use before shipping anything handling auth, untrusted input,
snowflake-architect
model: opus
Designs and audits Snowflake platforms — warehouse topology, RBAC hierarchy, pruning and clustering, streams/tasks/dynamic tables, Time Travel and cloning, and credit governance. Use for Snowflake des
sre-reliability
model: opus
Reviews and designs for reliability — SLIs/SLOs and error budgets, timeouts and retries, circuit breakers, backpressure, graceful degradation, health checks, progressive delivery, and alerting that pa
staff-engineer
model: opus
Use for system design, architecture decisions, and cross-module change planning — when the question is "how should this be built" or "what will this cost us later", not "write this function". Produces
test-engineer
model: opus
Designs and writes test suites — reproduction tests for bugs, boundary and error-path coverage, property-based tests, contract tests, and de-flaking. Use when a change needs tests that would actually
verifier
model: sonnet
Independently re-measures factual claims — test counts, coverage percentages, timings, line numbers, whether a command actually passes. Use when a report, plan, or commit message states numbers that o

Slash commands (12)

/adr/bootstrap/dbt-audit/deep-review/design/dq/rca/sf-audit/sf-tune/ship/standards/validate

Similar rigs

copied ✓