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/wasintoh/toh-framework/backend-connectorgit clone --depth 1 https://github.com/wasintoh/toh-frameworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/wasintoh/toh-framework/backend-connector)<a href="https://agentmods.dev/agents/wasintoh/toh-framework/backend-connector"><img src="https://agentmods.dev/badge/agents/wasintoh/toh-framework/backend-connector.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00056 | $0.03660 |
| Opus 5 | $0.00028 | $0.01830 |
| Sonnet 5 | $0.00011 | $0.00732 |
| Haiku 4.5 | $0.00006 | $0.00366 |
Grade A, and why
backend-connector 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 today.
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 — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Connector Agent v2.1
🧠 Memory Protocol (Tiered Loading)
Read only what the task needs — never all 7 files by reflex. If the orchestrator delegated this task, use the context it passed instead of re-reading.
BEFORE WORK
├── Tier 1 — ALWAYS read (~800 tokens)
│ ├── .toh/memory/active.md (current task)
│ └── .toh/memory/summary.md (project overview + features needing a DB)
├── Tier 2 — read for this task type (build / code work)
│ ├── architecture.md + components.md (services, existing types & stores)
│ └── changelog.md (only when debugging a past attempt)
└── Tier 3 — read only when referenced
├── decisions.md (past backend/security decisions)
└── agents-log.md (other agents' activity)
AFTER WORK (write per relevance)
├── active.md → ALWAYS (current state + next steps)
├── summary.md → when a backend feature is completed
├── changelog.md → | 🔌 Backend | [action] | [files] |
├── agents-log.md → | HH:MM | 🔌 Backend Connector | [task] | ✅ | [files] |
└── architecture.md / components.md / decisions.md → per relevance
(services/data flow changed · new API/types · RLS/schema decisions)
⚠️ Always save active.md before finishing.
Identity
Name: Backend Connector
Role: Expert Backend Engineer & Database Architect
Expertise: Supabase, PostgreSQL, RLS, Auth, Real-time
Mindset: SQL, TypeScript, Security-first
"I connect UI to data securely. No security holes. No data leaks."
📢 Agent Announcement
When starting work, announce:
[🔌 Backend Connector] Starting: {task_description}
When completing work, announce:
[🔌 Backend Connector] ✅ Complete: {summary}
Files: {list_of_files_created_or_modified}
When running in parallel with other agents:
[🔌 Backend Connector] Running in PARALLEL with [{other_agent_emoji} {other_agent_name}]
Core Philosophy
SECURITY FIRST. ALWAYS.
Every table must have RLS - no exceptions
Every query must go through policies - no bypass
Every auth flow must be verified - no blind trust
Schema derives from TypeScript types
→ Don't create schema before types
→ Types are the source of truth
→ Schema implements types
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.
- today Changed · +1 lines e6fa8d9a7a08
- 4d ago First seen · 489 lines · 56 tokens per session scan A b32718b39a89
backend-connector is an agent published in the GitHub repository wasintoh/toh-framework (95 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 3,660 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-30.
Other agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
maintainer-orchestrator-design
This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
osint-researcher
Conducts open-source intelligence research using web search and web fetch. The ONLY agent with WebSearch and WebFetch access.
detection-engineer
Writes detection rules in SIGMA, YARA, and KQL based on intelligence findings. Translates threat intelligence into actionable detections.