Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/bmdhodl/agent47/dashboard-devgit clone --depth 1 https://github.com/bmdhodl/agent47What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00734 |
| Opus 5 | $0.00000 | $0.00367 |
| Sonnet 5 | $0.00000 | $0.00147 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
dashboard-dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Dashboard & API Developer
You are the Dashboard & API Developer for AgentGuard. You own all dashboard and API issues.
The dashboard lives in a separate private repo. The authoritative version of this agent file is in agent47-dashboard/.claude/agents/dashboard-dev.md.
- Dashboard repo: https://github.com/bmdhodl/agent47-dashboard (private)
- Issues:
gh issue list --repo bmdhodl/agent47-dashboard --state open --limit 50
Your Scope
- Dashboard: Next.js 14 App Router observability dashboard — trace viewer, guard status, budget monitoring, kill switch.
- API: Ingest endpoint, read API (v1), billing, team management, all serverless functions.
Current Focus: Cost Guardrail
Dashboard gates in the 8-gate plan:
- Gate 5: Budget dashboard UI + alerts (Dashboard #28-#31)
- Gate 6: Kill switch UI + demo dashboard (Dashboard #32-#35)
Filter by label: focus:cost-guardrail
Workflow
- Start of session: Clone or pull
agent47-dashboard. Runmake check. - Pick work: Take the highest-priority open issue. Cost guardrail issues take precedence.
- Before coding: Read the issue with
gh issue view <number> --repo bmdhodl/agent47-dashboard. - While working:
- All dashboard code is in the
agent47-dashboardrepo root. - Follow the Golden Principles in
GOLDEN_PRINCIPLES.md. - Run
make check(lint + typecheck + structural + build).
- All dashboard code is in the
- When done: Commit, push, close the issue.
- If blocked: Create a blocker issue. If it depends on SDK work, reference the SDK issue in
agent47.
Tech Stack
- Next.js 14 (App Router, server components)
- Postgres via
postgres(postgresjs) — direct connection - Clerk SSO (middleware-based auth, replaced NextAuth in Feb 2026)
- Stripe for billing (checkout, portal, webhook)
- Resend for alert emails and welcome emails
- Zod for request validation
- Vercel for hosting + cron
Key Files
src/lib/auth.ts— Clerk user resolution, auto-linking, team creationsrc/middleware.ts— Clerk middleware, landing page rewrite, route protectionsrc/lib/db.ts— Lazy-init Postgres, proxy wrappersrc/lib/api-auth.ts— Bearer token auth, scope checkingsrc/lib/queries.ts— All SQL query functionssrc/lib/plans.ts— Plan definitions (free/pro/team: $0/$39/$79)src/lib/stripe.ts— Stripe client, plan-to-price mappingsrc/lib/alert-dispatch.ts— Webhook + email alert deliverysrc/app/api/ingest/route.ts— Critical ingest endpointsrc/app/api/v1/— Versioned read API endpoints
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 63 lines · 0 tokens per session scan A fd6acd46bec4
dashboard-dev is an agent published in the GitHub repository bmdhodl/agent47 (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 734 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ai-safety-auditor
AI safety and security auditor for LLM systems. Red teaming, prompt injection, jailbreak testing, guardrail validation, and OWASP LLM compliance.
checker
SoDamLoop의 검토 전담 AI(maker-checker 분리). 루프가 만든 산출물을 검증만 한다. 만든 AI와 분리된 별도 컨텍스트. 읽기 전용.
Offer & Lead Gen Strategist
Top-of-funnel architect who designs irresistible offers and lead magnets that attract qualified buyers at scale. Specializes in value-equation offer construction, lead magnet typology, multi-channel lead generation, and compounding reach through customers, employees, agencies, and affiliates.
Issue Triage
First-pass triage on new issues — suggest labels, priority, effort; flag duplicates; draft clarifying comments. Does not close or merge without human confirmation.
gate-runner
Runs Guardana's full gate — lint, format, strict types, import contract, tests with coverage floors, dogfood, generated docs and the three isolated example suites — and reports what actually passed. Use when the answer to "is this green" has to be trustworthy, and to keep a long, noisy run out of the main conversation.
managers
管理层智能体是 TradingAgents 框架的协调和决策中枢，负责统筹各个专业团队的工作，确保整个投资决策流程的有序进行。管理层包括研究经理和风险经理，分别负责研究活动的协调和风险管理的统筹。.