marconae/speq-skill
A light-weight and straightforward system for spec-driven development with Claude Code or OpenAI Codex. Written in Rust 🦀
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 marconae/speq-skill/.claude ./rig-speq-skill # inspect, then merge into .claude/ 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 marconae/speq-skill/.claude/skills/speq-adr-rules .claude/skills/speq-adr-rules $ npx degit marconae/speq-skill/.claude/skills/speq-audit .claude/skills/speq-audit $ npx degit marconae/speq-skill/.claude/skills/speq-cli .claude/skills/speq-cli $ npx degit marconae/speq-skill/.claude/skills/speq-code-guardrails .claude/skills/speq-code-guardrails $ npx degit marconae/speq-skill/.claude/skills/speq-code-review .claude/skills/speq-code-review $ npx degit marconae/speq-skill/.claude/skills/speq-code-tools .claude/skills/speq-code-tools $ npx degit marconae/speq-skill/.claude/skills/speq-design-philosophy .claude/skills/speq-design-philosophy $ npx degit marconae/speq-skill/.claude/skills/speq-ext-research .claude/skills/speq-ext-research $ npx degit marconae/speq-skill/.claude/skills/speq-git-discipline .claude/skills/speq-git-discipline $ npx degit marconae/speq-skill/.claude/skills/speq-git-operations .claude/skills/speq-git-operations $ npx degit marconae/speq-skill/.claude/skills/speq-implement-pr .claude/skills/speq-implement-pr $ npx degit marconae/speq-skill/.claude/skills/speq-implement .claude/skills/speq-implement $ npx degit marconae/speq-skill/.claude/skills/speq-mission .claude/skills/speq-mission $ npx degit marconae/speq-skill/.claude/skills/speq-plan-pr .claude/skills/speq-plan-pr $ npx degit marconae/speq-skill/.claude/skills/speq-plan-review .claude/skills/speq-plan-review $ npx degit marconae/speq-skill/.claude/skills/speq-plan .claude/skills/speq-plan $ npx degit marconae/speq-skill/.claude/skills/speq-planning .claude/skills/speq-planning $ npx degit marconae/speq-skill/.claude/skills/speq-record .claude/skills/speq-record $ npx degit marconae/speq-skill/.claude/skills/speq-spec-merge .claude/skills/speq-spec-merge $ npx degit marconae/speq-skill/.claude/skills/speq-writing-guardrails .claude/skills/speq-writing-guardrails
$ curl -fsSL --create-dirs -o .claude/agents/adr-audit-agent.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/adr-audit-agent.md $ curl -fsSL --create-dirs -o .claude/agents/architecture-agent.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/architecture-agent.md $ curl -fsSL --create-dirs -o .claude/agents/audit-agent.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/audit-agent.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/implementer-agent.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/implementer-agent.md $ curl -fsSL --create-dirs -o .claude/agents/implementer-expert-agent.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/implementer-expert-agent.md $ curl -fsSL --create-dirs -o .claude/agents/plan-reviewer.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/plan-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/planner-agent.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/planner-agent.md $ curl -fsSL --create-dirs -o .claude/agents/recorder-agent.md https://raw.githubusercontent.com/marconae/speq-skill/main/.claude/agents/recorder-agent.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 *)"
]
}
} Skills (20)
speq-adr-rulesspeq-auditspeq-clispeq-code-guardrailsspeq-code-reviewspeq-code-toolsspeq-design-philosophyspeq-ext-researchspeq-git-disciplinespeq-git-operationsspeq-implement-prspeq-implementspeq-missionspeq-plan-prspeq-plan-reviewspeq-planspeq-planningspeq-recordspeq-spec-mergespeq-writing-guardrails
Subagents (9)
| adr-audit-agent model: fable | ADR audit worker for spec-driven development spawned by the speq-audit orchestrator. Reads every ADR under specs/_decision/, applies the ADR gate from speq-adr-rules to each one, marks the ones that f |
| architecture-agent model: opus | Architecture draft worker for spec-driven development spawned by the speq-mission orchestrator in brownfield projects. Reads the codebase and any old mission.md architecture sections, writes a draft o |
| audit-agent model: opus | Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing. |
| code-reviewer model: opus | Adversarial code quality reviewer spawned by the speq-implement orchestrator after implementation completes. Reviews only the provided changed-files list against the plan and returns tagged findings — |
| implementer-agent model: sonnet | Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instea |
| implementer-expert-agent model: opus | Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — complex algorithms, concurrency, cross-file refactors, non-obvious correctness. |
| plan-reviewer model: opus | Adversarial plan review (diabolus advocatus) spawned by the speq-plan or speq-plan-pr orchestrator after planner-agent. Challenges intent fidelity, feasibility, requirement quality, task breakdown, de |
| planner-agent model: opus | Planning worker for spec-driven development spawned by the speq-plan or speq-plan-pr orchestrator. Performs the actual heavy planning — research synthesis, spec delta authoring, task decomposition — a |
| recorder-agent model: sonnet | Spec recording worker for spec-driven development spawned by speq-record orchestrator. Merges plan deltas into permanent specs and archives completed plans. |
Similar rigs
HGInsights/claude-code-setup
Production-tested Claude Code harness configuration: hooks, skills, subagents, and automated review loops
Pragmatist 1.9k tok ·
sodiumjoe/dotfiles
dotfiles
Skill Collector 1.1k tok ·
AizenvoltPrime/claude-setup
—
Pragmatist 1.2k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
Pragmatist 3.0k tok ·