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 dhruvmehra/makememe --skill memecligit clone --depth 1 https://github.com/dhruvmehra/makememeWrote 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/dhruvmehra/makememe/memecli)<a href="https://agentmods.dev/skills/dhruvmehra/makememe/memecli"><img src="https://agentmods.dev/badge/skills/dhruvmehra/makememe/memecli/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/dhruvmehra/makememe/memecli"><img src="https://agentmods.dev/badge/skills/dhruvmehra/makememe/memecli.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 | $0.00121 | $0.02820 |
| Opus 5.5 | $0.00048 | $0.01128 |
| Sonnet 5.5 | $0.00024 | $0.00564 |
| Haiku 4.5 | $0.00012 | $0.00282 |
Grade A, and why
meme 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> ad-hoc `python`/`curl`), do not guess template ids, and keep to one bare How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
meme
Generate memes from the command line. The meme command wraps the free
memegen.link API — no API key needed.
Prime directive. For any meme request, use this skill end-to-end and drive the
memeCLI directly. Do not reimplement it (no hand-built URLs, no ad-hocpython/curl), do not guess template ids, and keep to one bare--print-urlcommand. The Rules below are mandatory, not suggestions — follow them every time, including the very first.
Prerequisite
The meme command must be installed. Check with meme --list. If it's missing,
install it:
uv tool install makememe
# or: pipx install makememe
Rules (always follow)
These apply everywhere the tool runs — interactive Claude Code and CI/CD:
- Always go through the
memeCLI. Never hand-build amemegen.linkURL, never write ad-hoc Python/scripts to construct or fetch one, and never reimplement the escaping. The CLI handles path-segment escaping, line order, errors, and output — reproducing it by hand gets these wrong. - Discover template ids with
meme --list(or--list --json). Don't guess ids from memory — guessed ids (buttons,twobuttons, …) 404. List first, then use a verified id. - Parse output with
--json, read it directly. When you need the path/URL in a script, usememe ... --jsonand read the JSON fields. Do not pipe it throughpython3 -c,sed, orawkto extract values —--json/--print-urlalready give you exactly what you need. - In CI/CD, install and call the CLI (
pip install makememe→meme ... --print-url). Don'tcurlthe API or build URLs inline in a workflow step. - Keep it smooth — one clean command, no files. Default to
--print-url; do not download or save a file (-o,--open) unless the user explicitly asks for one. Runmemeas a single bare command — never pipe it intogrep/tail/awkor add redirects. A bare, consistentmeme ...shape means one permission approval covers every call and nothing is written to disk; piping turns each call into a new command the user has to approve again.
What ships with it
3 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.
- 1mo ago First seen · 197 lines · 121 tokens per session scan A 53fd797f8467
meme is a skill published in the GitHub repository dhruvmehra/makememe (2 stars, last pushed 4mo ago), licensed MIT. It adds 121 tokens to every session and 2,820 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
symaira-eraseme
Orchestrate GDPR/CCPA data broker removals using the Symaira EraseMe CLI. Automates opt-out campaigns, inbox triage, deadline tracking, and legal rebuttal generation against 1,200+ data brokers.
treat
Prune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.
team-coordination
Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, code-reviewer, tester), and synthesizing their work into cohesive deliverables. Use this for complex projects that require multiple specialized perspectives.
feature-implementation
Implement software features, fix bugs, and write production-quality code. Use this for hands-on development work including writing new code, modifying existing code, and debugging issues.
contribute-broker
Skill for AI agents (Claude Code, OpenClaw, Cursor, etc.).
cozempic-doctor
Run health checks on Claude Code configuration and sessions. Use when troubleshooting Claude Code issues. (cozempic — does not shadow Claude Code's built-in /doctor).