By Archit3115
Advisor→executor orchestration for Claude Code. One architect model (Fable) plans, cheaper specialists (Sonnet/Opus) build, GPT reviews — routed to the model that does each chunk best, under a token diet, over a live knowledge graph, with typeset output.
Karpathy-style overnight autoresearch loop — one hypothesis, one file, one budgeted experiment, one metric, keep-or-revert. Works for any task with a single measurable metric.
Build/refresh & query the project knowledge graph (graphify → OKF).
Produce a PDF the Seahorse way — LaTeX source compiled with tectonic. Never HTML-print.
Seahorse deep research — Opus researcher, primary sources (arXiv/ResearchGate), cited + verified.
Seahorse advisor plans a task — Fable decomposes it and assigns each chunk a model.
Seahorse ADVISOR — the architect. Fable-first planner that decomposes a task into a plan and assigns each chunk to the executor model that does it best. Read-only: it designs, it does not build. Invoke at the start of any non-trivial task, then delegate the chunks it returns.
Seahorse HEAVY BUILDER — Opus-tier executor for ambiguous, cross-cutting, or subtle implementation. Invoke for chunks the advisor marks Opus. Writes code under ponytail discipline and verifies its own work.
Seahorse LIGHT BUILDER — Sonnet-tier executor for mechanical, well-scoped, high-volume edits. Invoke for chunks the advisor marks Sonnet. Fast, minimal, style-matched.
Seahorse RESEARCHER — Opus-tier discovery and literature agent. Fan-out web + primary-source research (arXiv via alphaXiv, ResearchGate, web scraping), adversarial verification, cited synthesis. Invoke for any research, discovery, or "find out X from real sources" task.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Seahorse turns Claude Code into an advisor→executor orchestration layer: one architect model plans, cheaper specialist models build, every unit of work is routed to the model that does it best — under a strict token diet, over a live project knowledge graph, with typeset output.
Seahorse = the whole framework this repo installs. The token-discipline layer (caveman = talk less, ponytail = write less code) ships vendored in
vendor/.
| Concern | Tooling |
|---|---|
| Talk less / write less code | caveman + ponytail (vendored, MIT) |
| Plan → delegate → verify | Fable advisor → Sonnet/Opus executors → GPT (Codex) review |
| Research | /research, /deep-research, dynamic Workflows, arXiv (alphaXiv MCP), primary sources |
| Knowledge graph | graphify → OKF |
| Hold work across turns | /goal, /workflows |
| Outputs | PDFs = LaTeX/tectonic, diagrams = Mermaid |
| CI/CD | GitHub Actions templates (lint → type → test → build) |
See docs/architecture.md for the flow diagrams and the full routing table.
Seahorse ships two ways, because Claude Code has two extension models and each has a trade-off.
/seahorse:seahorseclaude plugin marketplace add Archit3115/seahorse
claude plugin install seahorse@seahorse
# optional companion token-discipline plugins (vendored in this repo):
claude plugin install caveman@seahorse ponytail@seahorse
Or ask Claude to do it for you after cloning — those are the two commands it runs.
Auto-install on clone: this repo carries a .claude/settings.json that pre-registers the marketplace
and enables the plugins. When you open Claude Code inside the cloned repo and trust the folder, Claude
Code can offer to install them without you typing the commands. This only affects sessions started in this
directory, and — being third-party code — it still asks for your consent. There is no silent
install-on-git clone; that would be a security hole, and Claude Code does not do it. If your version
doesn't prompt, run the two commands above.
Local dev without installing: claude --plugin-dir /path/to/seahorse.
~/.claude config — gives you the bare /seahorse commandPlugin skills are always namespaced (/seahorse:seahorse). If you want the bare /seahorse, run the
installer, which copies the contract, agents, and commands into ~/.claude:
./install.sh
It merges (never clobbers) your global CLAUDE.md, installs the four agents and four commands (including
the bare /seahorse), and wires the SessionStart bootstrap hook. Optional tooling it points you at:
tectonic (LaTeX PDFs), uv + graphifyy (knowledge graph), codex CLI + codex login (GPT review).
Which to pick: plugin for clean, versioned, shareable install; installer if you specifically want the
bare /seahorse and the global contract. They coexist — a --plugin-dir copy wins for its session.
seahorse/
├── .claude-plugin/
│ ├── plugin.json # plugin manifest (the seahorse plugin)
│ └── marketplace.json # marketplace: seahorse + vendored caveman + ponytail
├── .claude/settings.json # auto-install pre-config (trust-prompt, this dir only)
├── commands/ # /seahorse · /research · /kg · /pdf (namespaced under the plugin)
├── agents/ # advisor · researcher · builder-heavy · builder-light
├── hooks/
│ ├── hooks.json # plugin SessionStart hook
│ ├── seahorse-activate.sh # injects the compact operating contract
│ └── seahorse-bootstrap.sh # standalone-install project-bootstrap signal (gated to ~/Work)
├── contract/
│ ├── CLAUDE.global.md # → ~/.claude/CLAUDE.md (standing contract)
│ ├── CLAUDE.project.template.md # per-project contract template
│ └── settings.snippet.json # SessionStart hook snippet for the standalone install
├── vendor/ # caveman + ponytail forks (MIT, attribution preserved)
├── benchmarks/ # SWE-bench harness: Fable vs Opus vs Sonnet vs Seahorse
├── docs/architecture.md # Mermaid diagrams + routing table
├── templates/ci/ # node.yml · python.yml
└── install.sh # standalone ~/.claude installer
npx claudepluginhub archit3115/seahorse --plugin seahorseUltra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex and antigravity CLIs when installed) to get diverse perspectives on coding problems
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications