~ / rigs / rogadev / paceline

rogadev/paceline

A Claude Code status line that paces your usage limits and shows, at a glance, where every session stands.

↗ GitHub ★ 0 MIT updated 1mo ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.1k tokens
Featherweight · 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 rogadev/paceline/.claude ./rig-paceline  # 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 rogadev/paceline/.claude/skills/deep-review .claude/skills/deep-review
$ curl -fsSL --create-dirs -o .claude/agents/review-advisor.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-advisor.md
$ curl -fsSL --create-dirs -o .claude/agents/review-architecture.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-architecture.md
$ curl -fsSL --create-dirs -o .claude/agents/review-gate.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-gate.md
$ curl -fsSL --create-dirs -o .claude/agents/review-intent.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-intent.md
$ curl -fsSL --create-dirs -o .claude/agents/review-logic.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-logic.md
$ curl -fsSL --create-dirs -o .claude/agents/review-output.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-output.md
$ curl -fsSL --create-dirs -o .claude/agents/review-perf.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-perf.md
$ curl -fsSL --create-dirs -o .claude/agents/review-quality.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-quality.md
$ curl -fsSL --create-dirs -o .claude/agents/review-release.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-release.md
$ curl -fsSL --create-dirs -o .claude/agents/review-security.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-security.md
$ curl -fsSL --create-dirs -o .claude/agents/review-tests.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-tests.md
$ curl -fsSL --create-dirs -o .claude/agents/review-verifier.md https://raw.githubusercontent.com/rogadev/paceline/main/.claude/agents/review-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 (1)

Subagents (12)

review-advisor
model: opus
deep-review advisor for paceline. Takes the verified findings of a review and turns them into researched, plain-language recommendations - one clear problem and one recommended fix per finding, ground
review-architecture
model: sonnet
deep-review lane. Structure of a diff in paceline (the Claude Code status-line CLI) - cmd/paceline staying thin, one package per concern under internal/, dependency direction between internal packages
review-gate
model: haiku
deep-review lane. The automated check gate for paceline. Runs the repo's check-only commands (gofmt -l, go vet, go test, go test -race when cgo is available, the 90% coverage floor, golangci-lint and
review-intent
model: sonnet
deep-review lane. Alignment with requirements for paceline. Checks a diff against its GitHub issue (acceptance criteria, requirements, done-when), PR description, and commit messages, and reports each
review-logic
model: sonnet
deep-review lane. Correctness of paceline (a Go CLI status line for Claude Code) - the pace math, time zones and DST, JSON decoding of Claude Code's payload, config merging, error handling, file I/O f
review-output
model: sonnet
deep-review lane. What a paceline user sees - the rendered Claude Code status line (segment order, separators, spacing, glyphs and font coverage, truecolor and basic ANSI color, contrast on dark and l
review-perf
model: sonnet
deep-review lane. Cost per refresh for paceline (a Go CLI status line for Claude Code): process startup work, file reads and their size caps, allocations and regexp compilation on the hot path, the gi
review-quality
model: sonnet
deep-review lane. Maintainability and idiomatic Go quality of a diff in paceline (the Claude Code status-line CLI) - naming, function size, duplication (Rule of Three), dead code, error wrapping, zero
review-release
model: sonnet
deep-review lane. Release correctness and CI for paceline (github.com/rogadev/paceline): whether a commit's type matches its effect on the version, the semantic-release plugin chain and GoReleaser bui
review-security
model: opus
deep-review lane. Security reviewer for paceline, the Go Claude Code status line that strangers install and that runs on every refresh with the user's privileges. Reviews a diff for terminal escape in
review-tests
model: sonnet
deep-review lane. Test coverage and quality for a diff in paceline - whether changed logic has table-driven tests, hostile-input tests for anything paceline prints (escape sequences, bidi, zero-width,
review-verifier
model: opus
deep-review verifier for paceline. Skeptically re-checks every finding from every review lane against the actual code, the diff, and the app profile; confirms, downgrades, marks pre-existing, discards

Similar rigs

copied ✓