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 mupengi-bot/mupengism --skill insta-postgit clone --depth 1 https://github.com/mupengi-bot/mupengismWrote 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/mupengi-bot/mupengism/insta-post)<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/insta-post"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/insta-post/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/mupengi-bot/mupengism/insta-post"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/insta-post.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 | $0.00055 | $0.00674 |
| Opus 5 | $0.00028 | $0.00337 |
| Sonnet 5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
insta-post 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instagram Post Upload 🐧
Upload images as Instagram posts via OpenClaw browser tool (CDP port 18800).
Prerequisites
- OpenClaw browser running (port 18800)
- Instagram tab open and logged in
- Images in JPG format (PNG causes "문제가 발생했습니다" errors)
Quick Upload
For simple posts, use the bundled script:
node <skill-dir>/scripts/post.sh "<image_paths_comma_separated>" "<caption>"
Browser Tool Method (Recommended)
Step-by-step flow:
-
Snapshot —
browser snapshotto find the Instagram tab. SavetargetId. -
Close any dialogs — If settings/menus are open, press ESC or click outside.
-
Click "만들기" — Find "새로운 게시물 만들기" or "만들기" in sidebar. Click it.
-
Upload image — Find
input[type=file]via evaluate:document.querySelectorAll('input[type="file"]')Use the last one (usually index 2, accepts video+image). Upload via
browser upload. -
Wait 5 seconds — Let the image load.
-
Click "다음" — Crop screen → Next.
-
Click "다음" — Filter screen → Next.
-
Type caption — Find textarea with
aria-label="문구 입력...", click it, then type. -
Add collaborators (optional) — Before sharing:
- Click "사람 태그하기" or collaborator section
- Search and add your team account usernames
-
Click "공유하기" — Submit the post.
-
Verify — Wait for "게시물이 공유되었습니다" confirmation.
Image Preparation
- Format: JPG only. Convert PNG:
convert input.png -quality 92 output.jpg - Size: 1024x1024 or 1080x1080 recommended
- Multiple images: Upload multiple files to the same input for carousel
Collaborator Tagging
Configure your default collaborators in your workspace TOOLS.md file.
Troubleshooting
| Problem | Fix |
|---|---|
| "문제가 발생했습니다" | Convert PNG→JPG, refresh browser |
| act timeout | Re-snapshot, re-confirm refs |
| Settings dialog open | Press ESC or click outside |
| File input not found | Re-click "만들기" button |
| Caption won't type | Click textarea first, then type |
| Wrong element clicked | Always snapshot before clicking, verify ref |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 80 lines · 55 tokens per session scan A 6fd98d32fa2d
insta-post is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 674 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
agent-browser
Headless browser automation CLI. Open, browse, interact with, and screenshot web pages. Use when: opening websites, browser-based login, web app testing, taking screenshots, UI verification.