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 dcode-co/logi-plugins --skill logi-approvalgit clone --depth 1 https://github.com/dcode-co/logi-pluginsWrote 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/dcode-co/logi-plugins/logi-approval)<a href="https://agentmods.dev/skills/dcode-co/logi-plugins/logi-approval"><img src="https://agentmods.dev/badge/skills/dcode-co/logi-plugins/logi-approval/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/dcode-co/logi-plugins/logi-approval"><img src="https://agentmods.dev/badge/skills/dcode-co/logi-plugins/logi-approval.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 | $0.00110 | $0.00867 |
| Opus 5.5 | $0.00044 | $0.00347 |
| Sonnet 5.5 | $0.00022 | $0.00173 |
| Haiku 4.5 | $0.00011 | $0.00087 |
Grade A, and why
logi-approval 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
logi Agent Approval Gate
logi's Agent Approval Gate lets an AI agent pause and ask a human for explicit
approval — via a push notification with Face ID / passkey confirmation on
their phone — before performing an action that is expensive, irreversible, or
otherwise high-risk. The human sees a plain-language description of the
action and a 6-digit number_match code, and taps 승인(approve) or
거절(reject).
What this gate is for
- Changing an ads/marketing budget by more than ~20% or a large absolute amount
- Running migrations or destructive operations on a production database
- Sending bulk email/SMS (e.g. more than 100 messages in one batch)
- Spending above a threshold on any external paid API
- Deploying to production
- Any other action the project owner has flagged as requiring sign-off
If in doubt whether an action qualifies, treat it as high-risk and request approval rather than proceeding silently.
When to call the tool
The bundled logi-approval MCP server exposes two tools, named
logi__request_approval and logi__check_approval. Depending on the host,
they may appear under a namespaced full name — in Claude Code a
plugin-bundled server surfaces them as
mcp__plugin_logi-approval_logi-approval__logi__request_approval — so match
tools by the trailing name, not the exact prefix.
Call the request-approval tool before executing the risky action, not after. It blocks (or can be polled with the check-approval tool) until the user decides or the request times out.
logi__request_approval({
action_type: "ads.budget_change",
title: "Meta 광고 예산 변경",
body: "500,000 KRW → 5,000,000 KRW 로 10배 증액"
})
Rules:
- If the response
statusis not"approved", abort the action and tell the user it was rejected or timed out — never proceed anyway. - Do not batch multiple high-risk actions under one vague approval request;
each distinct risky action gets its own request with a specific
title/body. - Do not retry a rejected request immediately — a cool-down applies server-side.
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.
- 2mo ago First seen · 79 lines · 110 tokens per session scan A 3e29107a499d
logi-approval is a skill published in the GitHub repository dcode-co/logi-plugins (0 stars, last pushed 27d ago), licensed MIT. It adds 110 tokens to every session and 867 once invoked, about $0.0004 per session on Opus 5.5. 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.
logi-approval compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| logi-approvaldcode-co/logi-plugins | Skill | 0 | 27d ago | MIT | A | 110 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |