bks-lab/open-bridge
Stop re-explaining your work to your coding agent. Plain markdown and YAML in git, read at session start by Claude Code, Codex and Copilot CLI. MIT.
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 bks-lab/open-bridge/.claude ./rig-open-bridge # 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 bks-lab/open-bridge/examples/overlay-example/tree/skills/example-org-coordinator .claude/skills/example-org-coordinator $ npx degit bks-lab/open-bridge/skills/a2a .claude/skills/a2a $ npx degit bks-lab/open-bridge/skills/archive .claude/skills/archive $ npx degit bks-lab/open-bridge/skills/board-pilot .claude/skills/board-pilot $ npx degit bks-lab/open-bridge/skills/bridge-audit .claude/skills/bridge-audit $ npx degit bks-lab/open-bridge/skills/bridge-contribute .claude/skills/bridge-contribute $ npx degit bks-lab/open-bridge/skills/bridge-curator .claude/skills/bridge-curator $ npx degit bks-lab/open-bridge/skills/bridge-dashboard .claude/skills/bridge-dashboard $ npx degit bks-lab/open-bridge/skills/bridge-explorer .claude/skills/bridge-explorer $ npx degit bks-lab/open-bridge/skills/bridge-greeting .claude/skills/bridge-greeting $ npx degit bks-lab/open-bridge/skills/bridge-leak-check .claude/skills/bridge-leak-check $ npx degit bks-lab/open-bridge/skills/bridge-learn .claude/skills/bridge-learn $ npx degit bks-lab/open-bridge/skills/bridge-onboard .claude/skills/bridge-onboard $ npx degit bks-lab/open-bridge/skills/bridge-overlay .claude/skills/bridge-overlay $ npx degit bks-lab/open-bridge/skills/bridge-promote .claude/skills/bridge-promote $ npx degit bks-lab/open-bridge/skills/bridge-status .claude/skills/bridge-status $ npx degit bks-lab/open-bridge/skills/bridge-sync .claude/skills/bridge-sync $ npx degit bks-lab/open-bridge/skills/briefing .claude/skills/briefing $ npx degit bks-lab/open-bridge/skills/calendar .claude/skills/calendar $ npx degit bks-lab/open-bridge/skills/capability-broker .claude/skills/capability-broker $ npx degit bks-lab/open-bridge/skills/channel .claude/skills/channel $ npx degit bks-lab/open-bridge/skills/cmux .claude/skills/cmux $ npx degit bks-lab/open-bridge/skills/dashboard .claude/skills/dashboard $ npx degit bks-lab/open-bridge/skills/debrief .claude/skills/debrief $ npx degit bks-lab/open-bridge/skills/doc-system .claude/skills/doc-system $ npx degit bks-lab/open-bridge/skills/github-projects-manager .claude/skills/github-projects-manager $ npx degit bks-lab/open-bridge/skills/html-canvas .claude/skills/html-canvas $ npx degit bks-lab/open-bridge/skills/knowledge-repo-init .claude/skills/knowledge-repo-init $ npx degit bks-lab/open-bridge/skills/mail-draft .claude/skills/mail-draft $ npx degit bks-lab/open-bridge/skills/mandants .claude/skills/mandants $ npx degit bks-lab/open-bridge/skills/meeting-transcription .claude/skills/meeting-transcription $ npx degit bks-lab/open-bridge/skills/object-store .claude/skills/object-store $ npx degit bks-lab/open-bridge/skills/onboard-sim .claude/skills/onboard-sim $ npx degit bks-lab/open-bridge/skills/remote .claude/skills/remote $ npx degit bks-lab/open-bridge/skills/schedule .claude/skills/schedule $ npx degit bks-lab/open-bridge/skills/secrets .claude/skills/secrets $ npx degit bks-lab/open-bridge/skills/spec-kickoff .claude/skills/spec-kickoff $ npx degit bks-lab/open-bridge/skills/ta<redacted> .claude/skills/ta<redacted> $ npx degit bks-lab/open-bridge/skills/tracker-sync .claude/skills/tracker-sync $ npx degit bks-lab/open-bridge/skills/workload .claude/skills/workload
$ curl -fsSL --create-dirs -o .claude/agents/archivist.md https://raw.githubusercontent.com/bks-lab/open-bridge/main/.claude/agents/archivist.md $ curl -fsSL --create-dirs -o .claude/agents/code-analyst.md https://raw.githubusercontent.com/bks-lab/open-bridge/main/examples/agency/.claude/agents/code-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/deploy-engineer.md https://raw.githubusercontent.com/bks-lab/open-bridge/main/examples/agency/.claude/agents/deploy-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/ops-officer.md https://raw.githubusercontent.com/bks-lab/open-bridge/main/examples/agency/.claude/agents/ops-officer.md $ curl -fsSL --create-dirs -o .claude/agents/example-org-coordinator.md https://raw.githubusercontent.com/bks-lab/open-bridge/main/examples/overlay-example/tree/.claude/agents/example-org-coordinator.md $ curl -fsSL --create-dirs -o .claude/agents/paperwork-clerk.md https://raw.githubusercontent.com/bks-lab/open-bridge/main/examples/portfolio/.claude/agents/paperwork-clerk.md $ curl -fsSL --create-dirs -o .claude/agents/SPEC.md https://raw.githubusercontent.com/bks-lab/open-bridge/main/agents/_gateway/SPEC.md $ curl -fsSL --create-dirs -o .claude/agents/system-prompt.md https://raw.githubusercontent.com/bks-lab/open-bridge/main/agents/_template/system-prompt.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 (41)
example-org-coordinatora2aarchiveboard-pilotbridge-auditbridge-contributebridge-curatorbridge-dashboardbridge-explorerbridge-greetingbridge-leak-checkbridge-learnbridge-onboardbridge-overlaybridge-promotebridge-statusbridge-syncbriefingcalendarcapability-brokerchannelcmuxdashboarddebriefdoc-systemgithub-projects-managerhtml-canvasknowledge-repo-initmail-draftmandantsmeeting-transcriptionobject-storeonboard-simremoteschedulesecretsspec-kickoffta<redacted>tracker-syncworkloadworkspace
Subagents (8)
| archivist model: sonnet | Processes document intake in batches — scans filesystem and mail sources, classifies documents against routing rules, previews moves, executes approved moves, and logs to the audit trail. Use for larg |
| code-analyst model: sonnet | Investigates code-level issues in the agency's Python stack (Django, FastAPI, SQLAlchemy) — debugging, log analysis, query optimization, test-coverage gaps. Spawn for any read-heavy code investigation |
| deploy-engineer model: sonnet | Runs and verifies deployments for the agency's two client stacks — BigCorp on AWS (Terraform, Lambda, RDS) and StartupXYZ on Vercel — including CI pipelines, migrations, and secret management. Spawn f |
| ops-officer model: haiku | Keeps the agency's multi-client task boards clean — GitHub Projects V2 sync, field updates, weekly client status prep, iteration planning. Spawn for board grooming or status-report collection across B |
| example-org-coordinator model: haiku | Single entry point for the example-org engagement — board grooming on the example-board GitHub Project, status-report prep for the example-team mandant, and routing per rules/org/example-routing.md. S |
| paperwork-clerk model: haiku | Files receipts, invoices and letters to the right hat (company, freelance, private) using the persona destinations, and lists what is missing for a tax handover. Spawn for a batch of documents or a "w |
| SPEC | — |
| system-prompt | — |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| Stop | * | ${CLAUDE_PROJECT_DIR}/.claude/hooks/worklog-drift-check.sh |
Similar rigs
orwa-mahmoud/nightshift
Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results a clear view of what’s done, in progress, parked, or blocked—without scrolling a marathon chat.
Skill Collector 756 tok ·
SethGammon/Citadel
The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.
Orchestrator 38.0k tok ·
suboss87/FDEOps
Forward deployed engineering skills for AI coding agents.
Skill Collector 5.2k tok ·
Luke-Bradford/autonomy-engine
Repo-agnostic engine for running Claude Code autonomy loops against any target repo
Pragmatist 9.9k tok ·