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 TOKTOKHAN-DEV/agent-company --skill upload-assetsgit clone --depth 1 https://github.com/TOKTOKHAN-DEV/agent-companyWrote 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/toktokhan-dev/agent-company/upload-assets)<a href="https://agentmods.dev/skills/toktokhan-dev/agent-company/upload-assets"><img src="https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/upload-assets/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/toktokhan-dev/agent-company/upload-assets"><img src="https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/upload-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 39 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00002 | $0.01090 |
| Opus 5 | $0.00001 | $0.00545 |
| Sonnet 5 | $0.00000 | $0.00218 |
| Haiku 4.5 | $0.00000 | $0.00109 |
Grade A, and why
upload-assets 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 10d 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.
curl -X PUT \ How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
upload-assets
이 스킬의 경계
바이트를 올리는 것 당신
검토 요청 버튼을 누르는 것 사람
image_upload_url + PUT 은 CDN 에 파일을 올릴 뿐 아무것도 신청하지 않는다. 여기까지는
당신이 한다. 반면 miniapp_update_icon 과 miniapp_update_screenshots 는 이름과 달리
앱정보 검토를 함께 신청한다. 콘솔 웹의 "검토 요청" 버튼과 같다 — 부르지 마라.
코어 하드 룰 2번이다. 출고 버튼은 사람이 누른다.
올리기 전에
pnpm assets
규격 통과 가 아니면 올리지 마라. 해상도가 어긋난 파일은 업로드 자체는 되지만
(발급 단계는 확장자와 크기만 본다) 그 URL 을 쓰는 순간 거부된다.
올리는 절차
파일 하나마다 세 단계다. 순서를 바꾸면 실패한다.
1. 크기를 정확히 재고 발급받는다
image_upload_url(workspaceId, extension, contentLength)
→ uploadUrl · publicUrl · contentType
contentLength 는 실제 byte 수여야 한다. 어림수를 넣으면 PUT 이 거부된다.
uploadUrl 은 10분간 유효하다. 만료되면 다시 발급받는다.
2. PUT 으로 올린다
curl -X PUT \
-H 'Content-Type: {contentType}' \
-H 'x-amz-acl: public-read' \
--data-binary @{파일경로} \
'{uploadUrl}'
인증 헤더는 필요 없다. 두 헤더와 Content-Length 가 발급 조건과 다르면 거부된다. 완료 통지 도구는 없다 — PUT 이 성공하면 그것이 완료다.
3. publicUrl 을 기록한다
release/ 에 남긴다. 로컬 경로나 이 절차로 발급되지 않은 외부 URL 은 콘솔이 거부한다.
그다음 — 페이로드를 만들어 사람에게 넘긴다
miniapp_update_* 는 전체 페이로드를 다시 보내는 방식이다. 안 바꿀 값도 다 담아야
하고, 빠뜨리면 기존 값이 사라진다. 그러니 당신이 만들어 두고 사람이 누르게 한다.
miniapp_get 으로 지금 값을 가져와 그대로 옮긴다. 카테고리는 모양이 다르니 주의:
조회 (miniapp_get) |
요청 |
|---|---|
impression.categoryPaths[].category.id |
impression.categoryIds |
impression.categoryPaths[].subCategory.id |
impression.subCategoryIds |
impression.keywordList |
impression.keywordList (그대로) |
옮기지 않으면 기존 카테고리와 검색 키워드가 지워진다.
썸네일은 images[] 의 imageType=THUMBNAIL · orientation=HORIZONTAL 에 넣는다.
여기를 비우면 AI 자동 검수에서 썸네일 항목이 통째로 빠진다.
사람에게 넘길 때 반드시 보여줄 것
콘솔은 아래 5개에 모두 동의해야 검토 요청 버튼이 열린다. 당신이 대신 동의할 수 없다. 원문 그대로 보여주고 확인을 받아라.
- 앱인토스에서 오픈할 수 있는 서비스다
- 환전·현금화·자금세탁 우려가 있는 서비스가 아니다
- 서비스 운영에 필요한 인허가·등록·신고를 모두 마쳤다
- 부정행위를 조장하거나 신분증 위조 등 위법 행위를 포함하지 않는다
- 위반으로 문제가 생기면 모든 책임은 파트너사에 있고 토스에 생긴 손해를 보상한다
부르지 않는 도구
| 도구 | 왜 |
|---|---|
miniapp_update_icon · miniapp_update_screenshots |
검토 요청이 함께 나간다 |
miniapp_update_basic_info · miniapp_update_category |
같은 이유 |
review_submit · review_cancel |
검수 신청은 사람의 행위 |
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.
- 10d ago First seen · 105 lines · 2 tokens per session scan A 0ca8588dfe77
upload-assets is a skill published in the GitHub repository TOKTOKHAN-DEV/agent-company (77 stars, last pushed 13d ago), licensed MIT. It adds 2 tokens to every session and 1,090 once invoked, about $0.0000 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
capture-lessons
Ship and capture lessons workflow. Creates the PR, updates lessons learned, updates documentation, generates the sprint retrospective, and updates the backlog. Use at the end of a sprint cycle, or when the user says "ship", "capture", "lessons", "retro", "retrospective", "wrap up", or "done with this sprint". Also use…
red-team
Security red team that produces executable attack scripts and a static code audit. Use this skill for any security sprint, pre-release hardening, or when code touches authentication, billing, data storage, API endpoints, or secrets. Also use when the user says "red team", "pentest", "attack surface", "security audit"…
fix
Fix phase workflow. Fixes issues identified during code review, based on the triaged review output. Use after a review phase is complete and the human has triaged the findings, or when the user says "fix", "fix the issues", "address review feedback", or "apply fixes". Also use when the user says "fix these" after…
full-sprint
Orchestrates a complete sprint cycle autonomously. Each phase runs as a separate claude -p session for context isolation. Use when the sprint-directive.md is ready and the sprint should execute end-to-end. Also use when the user says "run a full sprint", "execute the sprint", "build everything", "autonomous sprint"…
runbook
Investigate production issues from symptom to structured report. Use this skill when something is broken, slow, or behaving unexpectedly in production or staging. Triggers on "it's broken", "users are reporting", "alert fired", "error in prod", "why is X slow", "investigate", "incident", "outage", "debug production"…
data-analysis
Fetch, query, and analyze project data. Use this skill when the user wants to investigate metrics, understand user behavior, debug a data issue, or answer a question that requires looking at real data. Triggers on "what happened", "why did X drop", "show me the numbers", "query", "metrics", "funnel", "cohort", "data"…