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 skills/moeru-ai/airi/upload-github-attachmentnpx skills add moeru-ai/airi --skill upload-github-attachmentgit clone --depth 1 https://github.com/moeru-ai/airiWrote 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/moeru-ai/airi/upload-github-attachment)<a href="https://agentmods.dev/skills/moeru-ai/airi/upload-github-attachment"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/upload-github-attachment.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.00425 |
| Opus 5 | $0.00032 | $0.00212 |
| Sonnet 5 | $0.00013 | $0.00085 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
upload-github-attachment scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Require the `gh` CLI and `curl`. What it actually says
Upload GitHub Attachment
Use the bundled script so authentication, repository resolution, MIME detection, and URL extraction remain consistent.
Requirements
- Require the
ghCLI andcurl. - Prefer an existing
gh auth loginsession. - When interactive
ghauthentication is unavailable, requireGH_TOKENorGITHUB_TOKENin the environment. - Stop and ask the user to configure one of those authentication methods if
gh auth tokencannot resolve a token. Never print, persist, or interpolate the token into diagnostic output.
Upload
Run from a checkout of the destination repository:
.agents/skills/upload-github-attachment/scripts/upload-github-attachment.sh /absolute/path/to/image.png
Specify the repository when the current directory cannot resolve it:
.agents/skills/upload-github-attachment/scripts/upload-github-attachment.sh \
--repo moeru-ai/airi \
/absolute/path/to/image.png
The script prints only the final https://github.com/user-attachments/assets/... URL. Embed it with  for an image or [label](URL) for another file.
Verification
- Request the returned URL and follow redirects.
- Require HTTP 200 and the expected content type.
- After creating or editing the GitHub content, reopen it and verify that the attachment renders.
The upload endpoint is currently undocumented by GitHub. Treat a rejected request as a blocking capability change instead of falling back to committing PR-only artifacts. Background and the observed Bearer-token flow: https://island94.org/2026/08/programmatically-upload-attachments-to-github-issues-pull-requests-comments.
What ships with it
2 files 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.
- 4d ago First seen · 42 lines · 65 tokens per session scan A 3a2acd63a2af
upload-github-attachment is a skill published in the GitHub repository moeru-ai/airi (48,699 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 425 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
claude_code
This document describes how a Claude Code agent (or any agent using the Claude Code CLI pattern) invokes the Seiðr-Smiðja forge through the Rúnstafr CLI bridge.
sap-extension-creator
Create Super Agent Party (SAP) extensions. This skill should be used when users want to create, build, or scaffold a new extension for Super Agent Party - including static HTML extensions (pure frontend) and Node.js backend extensions. Triggers on requests like "create a new SAP extension", "build an extension for…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
naga_control
通过 agentType: "nagacontrol" 调用，直接控制 Naga 自身的运行状态和配置。.
speak-status
Skill "speak-status" from kazakago/cc-mascot, covering cc mascot: 発話フィルタ状態の確認 and 手順.