agentrigs
+ submit rig
~ / rigs / joaovitorkc / harnessly

joaovitorkc/harnessly

Markdown-first toolkit that maps a repo, waits for approval, then installs the engineering harness coding agents actually need.

↗ GitHub ★ 1 NOASSERTION updated 9d ago personal setup Claude CodeCodexCursorCopilot
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.5k tokens
Featherweight · 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 joaovitorkc/harnessly/.claude ./rig-harnessly  # 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 joaovitorkc/harnessly/.agents/skills/harnessly-author-workflow .claude/skills/harnessly-author-workflow
$ npx degit joaovitorkc/harnessly/.agents/skills/harnessly-review-workflow .claude/skills/harnessly-review-workflow
$ npx degit joaovitorkc/harnessly/templates/standard/.agents/skills/verify-change .claude/skills/verify-change
$ curl -fsSL --create-dirs -o .claude/agents/prompt-reviewer.md https://raw.githubusercontent.com/joaovitorkc/harnessly/main/.claude/agents/prompt-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/prompt-reviewer.md https://raw.githubusercontent.com/joaovitorkc/harnessly/main/agents/prompt-reviewer.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)

harnessly-author-workflowharnessly-review-workflowverify-change

Subagents (2)

prompt-reviewer
model: inherit
Independently review Harnessly workflow changes for safety, contract integrity, applicability, portability, and evidence.
prompt-reviewerIndependently review Harnessly workflow changes for safety, contract integrity, applicability, portability, and evidence.

Cursor rules (3)

00-harnessly · always10-prompt-contract20-safety

Similar rigs

tigercosmos/terminal
A macOS-native terminal workspace designed for AI-driven development
★ 7 project Claude CodeCodexCursor 6 skills 1 hooks 2d ago
Pragmatist 1.1k tok ·
kartykk/agent-ready
Drop-in overlay for any coding agent (Claude, Cursor, Codex, Gemini, Qwen, Grok): one AGENTS.md, project map docs, skill catalog, local git and snapshots without GitHub, multi-AI handoff and voice alerts.
★ 0 project Claude CodeCodexCursor 19 skills 2 hooks 10d ago
Skill Collector 1.1k tok ·
fengshao1227/ccg-workflow
多模型协作工作流引擎 — /ccg:go 一个命令，AI 自动分析意图、选择策略、编排 Codex + Gemini + Claude 协作执行
★ 5,925 project Claude CodeCodex 20 skills 24d ago
Skill Collector 21.0k tok ·
BanKnight/claude-template
Claude Code workflow template with structured skills, runtime state, and long-term docs governance
★ 0 collection Claude CodeCodex 24 skills 5mo ago
Skill Collector 2.7k tok ·
copied ✓