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 skills add LEO0047/line-chat-advisor-mcp-ai-assistant --skill line-chat-advisorgit clone --depth 1 https://github.com/LEO0047/line-chat-advisor-mcp-ai-assistantWrote 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/skills/leo0047/line-chat-advisor-mcp-ai-assistant/line-chat-advisor)<a href="https://agentmods.dev/skills/leo0047/line-chat-advisor-mcp-ai-assistant/line-chat-advisor"><img src="https://agentmods.dev/badge/skills/leo0047/line-chat-advisor-mcp-ai-assistant/line-chat-advisor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leo0047/line-chat-advisor-mcp-ai-assistant/line-chat-advisor"><img src="https://agentmods.dev/badge/skills/leo0047/line-chat-advisor-mcp-ai-assistant/line-chat-advisor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00064 | $0.01029 |
| Opus 5 | $0.00032 | $0.00515 |
| Sonnet 5 | $0.00013 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
line-chat-advisor 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 11d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LINE Chat Advisor
Read one exact LINE chat through the line-readonly MCP, refresh it with DB
evidence, maintain private local relationship context, and return at most one
reply suggestion. All visible output is in Traditional Chinese (Taiwan).
Non-negotiable safety
- Never use Computer Use, Chronicle, OCR, screenshots, browser automation, or coordinates for LINE.
- Never call or invent
send_message,select_chat, generic input, clipboard, keyboard, Shell, AppleScript, or arbitrary app-control tools. - Never type, paste, focus a composer, press Return/Enter, or send anything.
- Never call
sync_older_messagesfor an ordinary latest-message request. - Never upload or quote private chat history outside the current answer. Do not put chat text, chat IDs, snapshots, or relationship context in a repository.
- Suggestions appear only in Codex.
Capability gate
Before reading any chat, confirm that the callable tool list contains all five
operations from the line-readonly MCP, regardless of namespace prefix:
line_statusrefresh_latestget_relationship_contextread_historysave_relationship_context
If any operation is absent, stop. Return one line telling the user the
line-readonly catalog is stale and Codex must be reloaded. Do not substitute
another tool or an older snapshot.
Required workflow
- Resolve the requested contact from the exact display name or a previously
successful
chatId. Never guess between duplicate names. - Call
line_status. Continue only whendbFound,keyAvailable,decryptOk,databaseSnapshot.readOnly, anddatabaseSnapshot.queryOnlyare all true. - Call
refresh_latestfor the exact chat withtimeoutSeconds: 30. Continue only whenok: trueandtargetAdvanced: true. Fortarget_not_advanced,locked_session_unavailable, focus/launch failure, or any other error, stop without calling context or history tools. - Call
get_relationship_contextfor the same exact chat. - If
initializedis false, callread_historywithorder: "oldest"andlimit: 200; follow everypagination.nextCursoruntilhasMoreis false. Only after all pages succeed, synthesize and save the relationship context. - If
initializedis true, callread_historywithorder: "oldest",limit: 200, andcursor: summaryThrough; paginate untilhasMoreis false. Merge only the newly read messages into the saved context. - Set
summaryThroughto the timestamp/message ID of the newest message that was actually read. Save these four concise, evidence-based fields:relationship,stableBackground,toneNotes, andavoidReasking. Never turn an inference into a fact. - Call
save_relationship_contextwith the context version returned by the preceding get. Oncontext_version_conflict, get the current context, rebase once, and retry once. If it conflicts again, stop.
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.
- 11d ago First seen · 98 lines · 64 tokens per session scan A 3c4ad479dbd7
line-chat-advisor is a skill published in the GitHub repository LEO0047/line-chat-advisor-mcp-ai-assistant (0 stars, last pushed 10d ago), licensed MIT. It adds 64 tokens to every session and 1,029 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 2026-08-31.
Other skills, from other repositories
browser
Use the installed OpenAI ChatGPT browser runtime through its noderepl MCP server.
doctor
Diagnose the local ChatGPT browser runtime bridge without reading browser content.
setup
Install the local ChatGPT browser runtime bridge for Claude Code.
dbear-mihomo-ai-failover
Diagnose and safely operate automatic proxy failover for ChatGPT, Codex, WorkBuddy (China), Kimi, MiniMax, and Mavis on macOS with Clash Verge Rev and Mihomo. Use when AI login fails, ChatGPT will not load, Codex spins or reports network errors, streaming stalls, or the user needs verified hard-failure detection…
dcf-model
Build discounted cash flow valuation workbooks in Excel.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.