~ / rigs / pham-canh / space-harness

pham-canh/space-harness

Model-agnostic harness kit for coding agents: capability profiles, context pruning, measured baselines. MIT.

↗ GitHub ★ 1 MIT updated 29d ago personal setup Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~365 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 pham-canh/space-harness/agents ./rig-space-harness/agents
$ npx degit pham-canh/space-harness/skills ./rig-space-harness/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 pham-canh/space-harness/skills/space-build .claude/skills/space-build
$ npx degit pham-canh/space-harness/skills/space-finish .claude/skills/space-finish
$ npx degit pham-canh/space-harness/skills/space-plan .claude/skills/space-plan
$ npx degit pham-canh/space-harness/skills/space-review .claude/skills/space-review
$ curl -fsSL --create-dirs -o .claude/agents/build.md https://raw.githubusercontent.com/pham-canh/space-harness/main/agents/build.md
$ curl -fsSL --create-dirs -o .claude/agents/locate.md https://raw.githubusercontent.com/pham-canh/space-harness/main/agents/locate.md
$ curl -fsSL --create-dirs -o .claude/agents/plan.md https://raw.githubusercontent.com/pham-canh/space-harness/main/agents/plan.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/pham-canh/space-harness/main/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/verify.md https://raw.githubusercontent.com/pham-canh/space-harness/main/agents/verify.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 (4)

Subagents (5)

build
model: opencode/space-bunny-free
Writes code and verifies it. Use when the plan is settled and files need to change.
locate
model: opencode/space-bunny-free
Finds where something lives and reports file:line evidence. Use before planning or changing anything, to close a gap in what is already known.
plan
model: opencode/space-bunny-free
Plans work before code exists. Use when a task is vague, spans more than a few files, or two people could disagree about what "done" means.
reviewer
model: opencode/space-bunny-free
Reviews work in two passes without editing. Use after a build step, before a commit or a release decision.
verify
model: opencode/space-bunny-free
Runs the project's checks and reports results. Use before claiming a task is done.

Similar rigs

copied ✓