ShamikM88/open-cam-framework
Open-source agentic credit underwriting framework. Gives you a first draft to build on: a full Credit Assessment Memorandum (CAM) or a research brief. A Maker-Checker pair of LLM agents drafts and audits; code enforces the financial and pol
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 23/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit ShamikM88/open-cam-framework/.claude ./rig-open-cam-framework # 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 ShamikM88/open-cam-framework/.claude/skills/annual-review .claude/skills/annual-review $ npx degit ShamikM88/open-cam-framework/.claude/skills/cam-change-verification .claude/skills/cam-change-verification $ npx degit ShamikM88/open-cam-framework/.claude/skills/credit-challenge .claude/skills/credit-challenge $ npx degit ShamikM88/open-cam-framework/.claude/skills/credit-risk .claude/skills/credit-risk $ npx degit ShamikM88/open-cam-framework/.claude/skills/deal-consistency .claude/skills/deal-consistency $ npx degit ShamikM88/open-cam-framework/.claude/skills/docs-maintenance .claude/skills/docs-maintenance $ npx degit ShamikM88/open-cam-framework/.claude/skills/evidence-discipline .claude/skills/evidence-discipline $ npx degit ShamikM88/open-cam-framework/.claude/skills/financial-analysis .claude/skills/financial-analysis $ npx degit ShamikM88/open-cam-framework/.claude/skills/information-gaps .claude/skills/information-gaps $ npx degit ShamikM88/open-cam-framework/.claude/skills/mutation-triage .claude/skills/mutation-triage $ npx degit ShamikM88/open-cam-framework/.claude/skills/policy-fit .claude/skills/policy-fit $ npx degit ShamikM88/open-cam-framework/.claude/skills/prompt-change-gate .claude/skills/prompt-change-gate
$ curl -fsSL --create-dirs -o .claude/agents/risk-reviewer.md https://raw.githubusercontent.com/ShamikM88/open-cam-framework/main/.claude/agents/risk-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/risk_reviewer_agent.md https://raw.githubusercontent.com/ShamikM88/open-cam-framework/main/agents/risk_reviewer_agent.md $ curl -fsSL --create-dirs -o .claude/agents/underwriter_agent.md https://raw.githubusercontent.com/ShamikM88/open-cam-framework/main/agents/underwriter_agent.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash|PowerShell",
"hooks": [
{
"type": "command",
"command": "if python3 -c 'pass' >/dev/null 2>&1; then python3 \"${CLAUDE_PROJECT_DIR}/.claude/hooks/deny_main_commit.py\"; else python \"${CLAUDE_PROJECT_DIR}/.claude/hooks/deny_main_commit.py\"; fi"
},
{
"type": "command",
"command": "python"
}
]
}
]
}
} Skills (12)
annual-reviewcam-change-verificationcredit-challengecredit-riskdeal-consistencydocs-maintenanceevidence-disciplinefinancial-analysisinformation-gapsmutation-triagepolicy-fitprompt-change-gate
Subagents (3)
| risk-reviewer model: inherit | The OpenCAM Risk Reviewer ("Checker"), run by the /review command in a fresh context to audit one saved draft against the deal's saved evidence. Read-only. Use only through /review, never to draft or |
| risk_reviewer_agent | — |
| underwriter_agent | — |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash|PowerShell | if python3 -c 'pass' >/dev/null 2>&1; then python3 "${CLAUDE_PROJECT_DIR}/.claude/hooks/deny_main_commit.py"; else python "${CLAUDE_PROJECT_DIR}/.claude/hooks/deny_main_commit.py"; fi |
| PreToolUse | Bash|PowerShell | python |
Slash commands (12)
/assemble/calibrate-policy/calibrate/collateral/commercial/committee-summary/project/research/review/spread/start-review/triage
Similar rigs
kyegomez/swarms
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
Pragmatist 8.9k tok · · Q5
CaptainCodeAU/claude-code-starter-kit
Batteries-included .claude/ templates for bootstrapping new projects with Claude Code. Smart hooks, lazy-loaded skills, and lean configs.
Automator 4.0k tok · · Q20
geovanneb/get-things-done
Local GTD workspace for executives: a kanban dashboard over plain Markdown files that Claude Code, Copilot and Codex can work with.
Pragmatist 2.2k tok · · Q23
Mohammed-Abdelhady/hyperflow
Rules, multi-session project memory, task templates, and a reviewed multi-agent chain for AI coding CLIs. Issue to PR when you need it.
Orchestrator 1.6k tok · · Q8