~ / rigs / Seismoforg / claude-config

Seismoforg/claude-config

Personal Claude Code config (CLAUDE.md + skills), Windows-wired via junction/@import

↗ GitHub ★ 1 no license updated 1mo ago personal setup Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~5.5k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Seismoforg/claude-config/agents ./rig-claude-config/agents
$ npx degit Seismoforg/claude-config/skills ./rig-claude-config/skills

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 Seismoforg/claude-config/skills/feature .claude/skills/feature
$ npx degit Seismoforg/claude-config/skills/git-commit .claude/skills/git-commit
$ npx degit Seismoforg/claude-config/skills/self-improve .claude/skills/self-improve
$ curl -fsSL --create-dirs -o .claude/agents/fable-agent.md https://raw.githubusercontent.com/Seismoforg/claude-config/main/agents/fable-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/haiku-agent.md https://raw.githubusercontent.com/Seismoforg/claude-config/main/agents/haiku-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/opus-agent.md https://raw.githubusercontent.com/Seismoforg/claude-config/main/agents/opus-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/sonnet-agent.md https://raw.githubusercontent.com/Seismoforg/claude-config/main/agents/sonnet-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 (3)

Subagents (4)

fable-agent
model: fable
Tier `fable` worker. Long-horizon autonomous work — a task spanning many steps whose shape is not knowable up front, where the brief states the goal and the route has to be found. Dispatched by a feat
haiku-agent
model: haiku
Recon worker. Read-only lookup and research — sweep a tree for every site of a pattern, read several files to answer one question, check whether a symbol is still referenced, find the precedent for a
opus-agent
model: opus
Tier `opus` worker. Work carrying a decision — rule or spec prose that states a rule, an exported signature or module boundary changing, an auth, session, input-handling or external-payload surface, o
sonnet-agent
model: sonnet
Tier `sonnet` worker. A new file, script or component that follows a pattern already present in the repo — the content is fixed by the brief, the form is yours to match. Dispatched by a feature's wave

Similar rigs

copied ✓