rlacombe/switchback-running
Ultrarunning training companion agent powered by Intervals.icu.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~7.4k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ npx degit rlacombe/switchback-running/.claude ./rig-switchback-running # 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 rlacombe/switchback-running/skills/adjust .claude/skills/adjust $ npx degit rlacombe/switchback-running/skills/archive .claude/skills/archive $ npx degit rlacombe/switchback-running/skills/briefing .claude/skills/briefing $ npx degit rlacombe/switchback-running/skills/check .claude/skills/check $ npx degit rlacombe/switchback-running/skills/nutrition .claude/skills/nutrition $ npx degit rlacombe/switchback-running/skills/race .claude/skills/race $ npx degit rlacombe/switchback-running/skills/review .claude/skills/review $ npx degit rlacombe/switchback-running/skills/setup .claude/skills/setup $ npx degit rlacombe/switchback-running/skills/today .claude/skills/today $ npx degit rlacombe/switchback-running/skills/week .claude/skills/week $ npx degit rlacombe/switchback-running/skills/why .claude/skills/why
$ curl -fsSL --create-dirs -o .claude/agents/activity-memory.md https://raw.githubusercontent.com/rlacombe/switchback-running/main/agents/activity-memory.md $ curl -fsSL --create-dirs -o .claude/agents/core.md https://raw.githubusercontent.com/rlacombe/switchback-running/main/agents/core.md $ curl -fsSL --create-dirs -o .claude/agents/memory-policy.md https://raw.githubusercontent.com/rlacombe/switchback-running/main/agents/memory-policy.md $ curl -fsSL --create-dirs -o .claude/agents/tool-policy.md https://raw.githubusercontent.com/rlacombe/switchback-running/main/agents/tool-policy.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 *)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| intervals-icu env: INTERVALS_API_KEY, INTERVALS_ATHLETE_ID | local / custom | 2.5k |
| strava env: STRAVA_CLIENT_ID, STRAVA_CLIENT_SECRET, STRAVA_REFRESH_TOKEN | local / custom | 2.5k |
Skills (11)
Subagents (4)
| activity-memory | — |
| core | — |
| memory-policy | — |
| tool-policy | — |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | bash scripts/auto-update.sh 2>/dev/null || true |
Similar rigs
dymchenkko/claude-study-agent
AI study agent for university courses, built on Claude Code. Learns from your own slides, PDFs and lecture recordings, quizzes you with spaced repetition, tracks mistakes, and builds mock exams.
Pragmatist 2.5k tok · · Q15
Barac9492/adjutant
Forkable Claude Code operating system for turning open decisions and scattered notes into action.
Skill Collector 1.8k tok · · Q0
OlegTestov/prove-it-mini
A pytest Stop hook for Claude Code: two repair attempts, then an explicit unverified result. No model calls, MIT.
Minimalist 332 tok · · Q3
rodrigomanhaes/flowyeah
Plan-to-PR pipeline for Claude Code.
Minimalist 2.1k tok · · Q8