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 instructions/junghoonghae/openkakao-cli/agents-mdgit clone --depth 1 https://github.com/JungHoonGhae/openkakao-cliWhat 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 | $0.00735 | $0.00735 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
openkakao-cli AGENTS.md 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 3d 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.
AI Agent Integration Guide
openkakao-cli is designed for AI agent integration. All commands support --json for structured output.
Safety Model
LOCO write operations (send, delete, edit, react) are disabled by default to prevent account bans.
Safe commands (always available, no server contact)
# Read chats from local KakaoTalk database (SQLCipher, no network)
openkakao-cli local-chats --json
openkakao-cli local-read <chat_id> -n 30 --json
openkakao-cli local-search "keyword" --json
openkakao-cli local-schema
# Preview actions without executing
openkakao-cli send 123 "message" --dry-run --json
openkakao-cli delete 123 456 --dry-run --json
Safe commands (REST API, lower risk)
openkakao-cli chats --json
openkakao-cli read <chat_id> --rest --json
openkakao-cli friends --json
openkakao-cli me --json
openkakao-cli doctor --json
Risky commands (require opt-in)
These require allow_loco_write = true in ~/.config/openkakao/config.toml:
openkakao-cli send <chat_id> "message" -y --json
openkakao-cli send --me "test" -y --json # Send to memo chat
openkakao-cli delete <chat_id> <log_id> -y --json
openkakao-cli edit <chat_id> <log_id> "new" -y --json
openkakao-cli react <chat_id> <log_id> --json
Unattended Mode
For fully non-interactive operation:
openkakao-cli --unattended --allow-non-interactive-send send <chat_id> "msg" -y --json
Or configure in ~/.config/openkakao/config.toml:
[mode]
unattended = true
[send]
allow_non_interactive = true
[safety]
allow_loco_write = true
min_unattended_send_interval_secs = 10
Recommended Agent Workflow
- Read with
local-chats/local-read(zero risk) - Preview with
--dry-runbefore any write - Execute only after user confirmation
- Prefer
--meflag for testing sends
JSON Output
All commands with --json return structured JSON to stdout. Diagnostic messages go to stderr.
# List chats
openkakao-cli local-chats --json
# Returns: [{"chat_id": 123, "chat_type": 0, "chat_name": "...", ...}]
# Read messages
openkakao-cli local-read 123 --json
# Returns: [{"log_id": 456, "chat_id": 123, "sender_name": "...", "message": "...", ...}]
# Dry-run
openkakao-cli send 123 "hello" --dry-run --json
# Returns: {"dry_run": true, "action": "send", "chat_id": 123, "message": "..."}
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.
- 3d ago First seen · 98 lines · 735 tokens per session scan A cec88f155df3
openkakao-cli AGENTS.md is an instructions file published in the GitHub repository JungHoonGhae/openkakao-cli (119 stars, last pushed 1mo ago), licensed MIT. It adds 735 tokens to every session, about $0.0037 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 instructions, from other repositories
ida-pro-mcp CLAUDE.md
Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.
reverse-engineering-assistant CLAUDE.md
Instructions for cyberkaida/reverse-engineering-assistant, covering claude.md, project overview, build and test commands, java extension (ghidra plugin) and set ghidra installation directory first.
wispterm AGENTS.md
Instructions for xuzhougeng/wispterm, covering agents.md, architecture, ui presentation styles, cohesion and coupling and integration layer vs feature domains.
HomeClaw AGENTS.md
Instructions for omarshahine/HomeClaw, covering homeclaw, architecture, project structure, build system and xcode version.
best-claude-hud AGENTS.md
Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.
moonproxy-desktop AGENTS.md
Instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.