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 lisamsung/agent-meme-forge --skill generate-meme-gif-packgit clone --depth 1 https://github.com/lisamsung/agent-meme-forgeWrote 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/lisamsung/agent-meme-forge/generate-meme-gif-pack)<a href="https://agentmods.dev/skills/lisamsung/agent-meme-forge/generate-meme-gif-pack"><img src="https://agentmods.dev/badge/skills/lisamsung/agent-meme-forge/generate-meme-gif-pack/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/lisamsung/agent-meme-forge/generate-meme-gif-pack"><img src="https://agentmods.dev/badge/skills/lisamsung/agent-meme-forge/generate-meme-gif-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00974 |
| Opus 5.5 | $0.00000 | $0.00390 |
| Sonnet 5.5 | $0.00000 | $0.00195 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
generate-meme-gif-pack 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Meme GIF Pack
Core rule: 没人用的表情包就是垃圾表情包. Every sticker must pass the sendability gate: real chat-use trigger, readable gag, and concrete send scenario.
Quick Decision
| User request | Route |
|---|---|
| Reference image or text concept -> Chinese meme GIF pack | Run intake, then plan-pack or plan-wizard. |
| Wants full automation / concurrency / API generation | Use image_provider=openai_images_api, then generate-raw-batch, then QC/build. |
| Wants Codex built-in image generation | Use image_provider=codex_builtin_image_gen; this is interactive and split across turns. |
| Already has raw PNG/GIF files | Use external_files, then accept-generated/QC/build. |
| Explicit Google AI Studio / Hermes / Nano Banana route | Switch to generate-meme-gif-pack-ai-studio. |
| Wants WeChat platform upload | First build and QC locally, then read references/wechat-platform-upload.md. |
Required Intake
Ask these unless the user already answered or explicitly said to use defaults:
- input: reference image or
text_concept - persona: e.g.
科研打工人,都市丽人,码农,学生,研究僧 - style:
clean-sticker,pixel-art,chibi,retro-msn,office-cartoon,hand-drawn - mode and count: WeChat uses 16 or 24; 18 is
self_use - quality mode:
submission,standard, orpreview - image provider:
codex_builtin_image_gen,openai_images_api,external_files, orai_studio_hermes
Use scripts/meme_pack.py plan-wizard when the user wants command-line guidance.
Tool Boundary
Codex built-in image_gen is a terminal action in this environment: call it only as the final action of the current turn, then resume next turn after the image has been saved/exported locally. Do not run accept-generated, qc-sheet, or build-preview in the same turn after built-in image_gen.
For full automation, do not use built-in image_gen; use the scriptable openai_images_api provider. Details: references/tool-boundary.md.
Required References
Read only what the situation needs:
What ships with it
18 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.
- assets/fonts/OFL.txt 4.3 KB
- assets/fonts/ZCOOLKuaiLe-Regular.ttf 1479 KB
- references/agent-rules.md 2.3 KB
- references/commands.md 2.1 KB
- references/dense-frames.md 5.2 KB
- references/meme-library.md 1.9 KB
- references/personas.md 2.0 KB
- references/pressure-scenarios.md 1.1 KB
- references/prompt-rules.md 20 KB
- references/qc-checklist.md 1.2 KB
- references/styles.md 1.5 KB
- references/tool-boundary.md 1.6 KB
- references/wechat-platform-upload.md 5.0 KB
- references/wechat-spec.md 4.3 KB
- references/workflow.md 2.1 KB
- scripts/dense_frames.py 7.5 KB runs code
- scripts/imagegen_client.py 8.0 KB runs code
- scripts/meme_pack.py 214 KB runs code
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.
- 1mo ago First seen · 76 lines · 0 tokens per session scan A cf79edf3f32e
generate-meme-gif-pack is a skill published in the GitHub repository lisamsung/agent-meme-forge (99 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 974 tokens. 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.
Other skills, from other repositories
ai-text-detector-github
Detect whether a passage shows AI-like writing signals and return an explainable risk estimate with confidence, caveats, and next steps.
usage-kernel
Use the six Codex Usage Tracker tools for exact local usage facts, bounded exploration, allowance observations, and evidence timelines.
pydantic
Python data validation using type hints and runtime type checking with Pydantic v2's Rust-powered core.
psy-ana-coder
Generate, modify, or debug reproducible R or Python analysis code from a completed analysis config YAML or concrete existing script. Use for data import/cleaning, statistical models, assumption checks, effect sizes, sensitivity analyses, publication figures, reports, session information, and analysis-script runtime…
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
python-anti-patterns
Common Python anti-patterns and a pre-merge review checklist.