generate-cover

generate-cover is a skill for Claude Code, Codex from TOKTOKHAN-DEV/agent-company. It costs 2 tokens per session (658 once invoked), scanned A, original, MIT.

A workflow for creating a cover image for a blog post by turning its subject into a visual scene and saving the generated image with its alternative text.

In plain words
What is it for?
Use it to create post-cover artwork, provide accessible descriptions, record the image prompt, and audit the resulting content image.
Why use it?
It avoids vague image prompts, unreadable text in generated images, and cover files whose post metadata has not been updated or checked.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to create post-cover artwork, provide accessible descriptions, record the image prompt, and audit the resulting content image.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toktokhan-dev/agent-company/generate-cover
Install

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.

Any agent
npx skills add TOKTOKHAN-DEV/agent-company --skill generate-cover
Clone the repo
git clone --depth 1 https://github.com/TOKTOKHAN-DEV/agent-company

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for generate-cover

README.md
[![agentmods](https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/generate-cover/github.svg)](https://agentmods.dev/skills/toktokhan-dev/agent-company/generate-cover)
Your own site
<a href="https://agentmods.dev/skills/toktokhan-dev/agent-company/generate-cover"><img src="https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/generate-cover/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.

agentmods 80×15 button for generate-cover

Your own site · 80×15
<a href="https://agentmods.dev/skills/toktokhan-dev/agent-company/generate-cover"><img src="https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/generate-cover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 658 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00002 $0.00658
Opus 5 $0.00001 $0.00329
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured 10d ago against content hash bcec8ea2eb12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

generate-cover 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 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.

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.

templates/blog/files/agents/image-maker/skills/generate-cover/SKILL.md · 70 lines

What it actually says

generate-cover

1. 프롬프트 작성

글의 주제를 시각적 장면으로 번역한다. 글 제목을 그대로 넣지 않는다.

좋은 프롬프트 나쁜 프롬프트
겹쳐진 반투명 문서 레이어가 하나의 흐름으로 정렬되는 추상 구성 AI 블로그 자동화에 관한 이미지
구체적 장면 · 구도 · 색조 글 제목 복사

텍스트가 들어간 이미지를 요청하지 않는다. 생성된 글자는 대부분 깨진다.

스타일은 기존 커버와 맞춘다. 기본 프리셋은 스크립트가 붙인다: clean editorial illustration, flat vector, muted palette, no text, no lettering

2. 생성

pnpm imagegen --slug <post-slug> --prompt "<장면 설명>" --alt "<대체 텍스트>"

스크립트가 하는 일:

  1. imagegen으로 이미지 생성 → apps/web/public/images/posts/<slug>.png
  2. scripts/set-cover.mjs로 프론트매터 cover 갱신 (source: codex-imagegen, origin에 프롬프트 기록)

--alt를 생략하면 프롬프트가 대체 텍스트로 쓰인다. 대체 텍스트는 보이는 것을 설명해야 하므로, 프롬프트가 그대로 쓰기에 부적절하면 직접 지정한다.

호출 방식이 다를 때

CLI 버전에 따라 인터페이스가 다르면 환경 변수로 덮어쓴다.

CODEX_IMAGEGEN_CMD='codex imagegen --out {out} "{prompt}"' \
  pnpm imagegen --slug <slug> --prompt "..."

{out}{prompt}가 치환된다.

3. 확인

ls -la apps/web/public/images/posts/
pnpm audit:content <slug>

[images] lane에 error가 없어야 한다.

실패 처리

3회까지 재시도한다. 프롬프트를 단순하게 바꿔가며 시도한다 (요소 수를 줄이고, 추상도를 높인다).

3회 실패하면 skills/fallback-image로 넘어간다. 다른 이미지 생성 모델이나 API를 찾지 않는다.

하지 않을 것

  • 실제 생성이 아닌 이미지에 source: codex-imagegen을 붙이지 않는다. 감사에서 걸리고, 걸리지 않아도 거짓 기록이다.
  • 본문이나 seo/geo 필드를 수정하지 않는다.
  • cover.alt를 비워두지 않는다. 접근성 문제이자 발행 차단 사유다.
Changes

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.

  1. 10d ago First seen · 70 lines · 2 tokens per session scan A bcec8ea2eb12

Subscribe to this mod's changes

generate-cover is a skill published in the GitHub repository TOKTOKHAN-DEV/agent-company (77 stars, last pushed 14d ago), licensed MIT. It adds 2 tokens to every session and 658 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

sc-skill

Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.

jazzyalex/agent-sessions · 55 tokens

memstack-content-youtube-script

Use this skill when the user says 'YouTube script', 'video script', 'write script for YouTube', 'YouTube video outline', or is creating scripted content for a YouTube video with hooks, chapters, and CTAs. Do NOT use for TikTok/Reels short-form scripts or webinar presentations.

cwinvestments/memstack · 70 tokens

memstack-marketing-facebook-ad

Use this skill when the user says 'facebook ad', 'FB ad', 'Meta ad', 'Instagram ad', or needs social media ad copy with targeting, creative direction, and A/B test plans for Meta Ads Manager. Do NOT use for Google search ads or organic social content.

cwinvestments/memstack · 64 tokens

memstack-content-tiktok-script

Use this skill when the user says 'TikTok script', 'TikTok video', 'Reels script', 'Shorts script', 'short-form video', or needs timestamped scripts with hooks, visual cues, and captions for 15-60 second videos. Do NOT use for Twitter threads or webinar scripts.

cwinvestments/memstack · 70 tokens

presentation-creator

Builds decks with a story spine, house visual system, setting-specific density, and speaker notes. Use when asked to "create a presentation", "write a pitch deck", or "turn this doc into slides". Defaults to Marp; use an available presentation tool for editable PowerPoint. For product UI use ui-design.

mblode/agent-skills · 69 tokens

yt-dlp-downloader

Generate and run yt-dlp download commands with probe-driven format selection, safe output naming, retry defaults, and structured execution reports. Use when users want to download videos, extract audio, fetch playlists, grab subtitles, handle authenticated/age-gated content, or download live streams. Covers single…

johnqtcg/awesome-skills · 96 tokens