sentientsky/ForgeLoop
A GitHub starter template for disciplined, token-aware AI-assisted engineering.
stack: Python
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit sentientsky/ForgeLoop/.claude ./rig-forgeloop # 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 sentientsky/ForgeLoop/.claude/skills/align .claude/skills/align $ npx degit sentientsky/ForgeLoop/.claude/skills/capture .claude/skills/capture $ npx degit sentientsky/ForgeLoop/.claude/skills/check .claude/skills/check $ npx degit sentientsky/ForgeLoop/.claude/skills/deepen .claude/skills/deepen $ npx degit sentientsky/ForgeLoop/.claude/skills/discover .claude/skills/discover $ npx degit sentientsky/ForgeLoop/.claude/skills/frame .claude/skills/frame $ npx degit sentientsky/ForgeLoop/.claude/skills/opencli-integrated .claude/skills/opencli-integrated $ npx degit sentientsky/ForgeLoop/.claude/skills/pack-context .claude/skills/pack-context $ npx degit sentientsky/ForgeLoop/.claude/skills/probe .claude/skills/probe $ npx degit sentientsky/ForgeLoop/.claude/skills/refresh-memory .claude/skills/refresh-memory $ npx degit sentientsky/ForgeLoop/.claude/skills/simplify .claude/skills/simplify $ npx degit sentientsky/ForgeLoop/.claude/skills/tdd .claude/skills/tdd $ npx degit sentientsky/ForgeLoop/.claude/skills/verify-completion .claude/skills/verify-completion $ npx degit sentientsky/ForgeLoop/.claude/skills/worktree-lifecycle .claude/skills/worktree-lifecycle
$ curl -fsSL --create-dirs -o .claude/agents/adversarial-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/adversarial-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/api-contract-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/api-contract-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/architecture-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/architecture-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/correctness-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/correctness-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/data-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/data-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/docs-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/docs-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/governance-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/governance-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/maintainability-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/maintainability-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/performance-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/performance-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/reliability-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/reliability-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-reviewer.md https://raw.githubusercontent.com/sentientsky/ForgeLoop/main/.claude/agents/test-reviewer.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 (14)
aligncapturecheckdeependiscoverframeopencli-integratedpack-contextproberefresh-memorysimplifytddverify-completionworktree-lifecycle
Subagents (12)
| adversarial-reviewer model: inherit | Use proactively for high-risk changes to challenge assumptions, abuse paths, and optimistic implementation claims. |
| api-contract-reviewer model: inherit | Use proactively to review CLI, JSON, template, plugin, and integration contracts for compatibility and drift. |
| architecture-reviewer model: inherit | Use proactively to review changes for system shape, boundaries, coupling, dependency direction, and maintainability. |
| correctness-reviewer model: inherit | Use proactively to check whether the implementation actually satisfies the requested behaviour and edge cases. |
| data-reviewer model: inherit | Use proactively to review memory records, indexes, frontmatter, capture quality, and data retention risk. |
| docs-reviewer model: inherit | Use proactively to review documentation clarity, beginner usability, knowledge capture, examples, and whether the change compounds. |
| governance-reviewer model: inherit | Use for memory features or integrations that may process personal data, provenance, retention, audit events, access control, or erasure claims. |
| maintainability-reviewer model: inherit | Use proactively to review whether the change is understandable, small, maintainable, and aligned with local patterns. |
| performance-reviewer model: inherit | Use proactively to review token load, runtime cost, file scanning cost, caching, and avoidable repeated work. |
| reliability-reviewer model: inherit | Use proactively to review failure handling, retries, timeouts, portability, and recovery paths. |
| security-reviewer model: inherit | Use proactively to review changes for secrets, unsafe input handling, authentication, authorisation, injection risk, and insecure defaults. |
| test-reviewer model: inherit | Use proactively to review validation quality, missing tests, weak assertions, flaky checks, and the definition of done. |
Cursor rules (1)
forgeloop · always
Kiro (3 steering)
How Kiro files are scored: methodology.
Similar rigs
chase0213/dotfiles-claude
—
Orchestrator 1.8k tok · · Q20
Tamircohen28/tamirs-superpowers
A portable agent toolkit — 31 skills, 10 specialist agents, worktree hooks and MCP stubs — shipped from one canonical source to six agent surfaces across five platforms: Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI and OpenCode.
Orchestrator 7.0k tok · · Q18
kimgoetzke/coding-agent-configs
My personal skills, agents, and other configuration files for agentic coding.
Orchestrator 2.0k tok · · Q23
morodomi/dev-crew
AI development team as a Claude Code plugin -- TDD workflow, security audit, and phase-boundary compaction.
Orchestrator 4.1k tok · · Q30