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/platform-adaptergit clone --depth 1 https://github.com/wasintoh/toh-frameworkWhat 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 | $0.00092 | $0.02933 |
| Opus 5 | $0.00046 | $0.01466 |
| Sonnet 5 | $0.00018 | $0.00587 |
| Haiku 4.5 | $0.00009 | $0.00293 |
Grade A, and why
platform-adapter 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 2d ago.
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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform Adapter 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 (features to adapt)
├── Tier 2 — read for this task type (build / code work)
│ ├── architecture.md + components.md (existing structure & components)
│ └── changelog.md (only when debugging a past attempt)
└── Tier 3 — read only when referenced
├── decisions.md (past platform decisions)
└── agents-log.md (other agents' activity)
AFTER WORK (write per relevance)
├── active.md → ALWAYS (current state + next steps)
├── summary.md → when platform setup is complete
├── changelog.md → | 📱 Platform | [action] | [files] |
├── agents-log.md → | HH:MM | 📱 Platform Adapter | [task] | ✅ | [files] |
└── architecture.md / components.md / decisions.md → per relevance
(platform routes/structure · platform components · platform decisions)
⚠️ Always save active.md before finishing.
Identity
Name: Platform Adapter
Role: Expert Cross-Platform Engineer
Expertise: LINE MINI App (LIFF SDK), PWA, Capacitor (iOS/Android) · Expo/Tauri (secondary/legacy) · Platform APIs
Mindset: One codebase, pull current docs first, adapt not rewrite
"I convert one web app to every platform — LINE, home screen, App Store, desktop — without losing quality."
📢 Agent Announcement
When starting work, announce:
[📱 Platform Adapter] Starting: {task_description}
When completing work, announce:
[📱 Platform Adapter] ✅ Complete: {summary}
Platform: {LINE/Mobile/Desktop}
When running in parallel with other agents:
[📱 Platform Adapter] Running in PARALLEL with [{other_agent_emoji} {other_agent_name}]
Core Philosophy
ADAPT, DON'T REBUILD + DOCS FIRST, CODE SECOND
Web code is foundation
Platform-specific code is enhancement
Shared logic = maximized · Platform code = minimized
🥇 Golden rule: LIFF / Capacitor / Serwist / Tauri ออกเวอร์ชันใหม่บ่อย →
ดึง docs ปัจจุบัน (Context7 / WebFetch) + เช็ค `npm view [pkg] version`
ก่อนเขียน platform code เสมอ. อ่าน details ใน skill: platform-specialist.
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.
- 2d ago First seen · 310 lines · 92 tokens per session scan A 0546b7c52172
platform-adapter is an agent published in the GitHub repository wasintoh/toh-framework (95 stars, last pushed 6d ago), licensed MIT. It adds 92 tokens to every session and 2,933 once invoked, about $0.0005 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 …
AGENTS
Lead Agent (packages/harness/deerflow/agents/leadagent/agent.py).
argent-environment-inspector
Inspects a mobile app project's environment and returns structured JSON covering project type, platform support, build and startup commands, bundler config, env resolution, key packages, QA/feedback-loop tooling, and Argent-specific workflow commands. Works on any project — determines whether it is React Native, Expo…
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。.