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.
git clone --depth 1 https://github.com/sytungan/emoji-speakWrote 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/commands/sytungan/emoji-speak/emoji)<a href="https://agentmods.dev/commands/sytungan/emoji-speak/emoji"><img src="https://agentmods.dev/badge/commands/sytungan/emoji-speak/emoji/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/commands/sytungan/emoji-speak/emoji"><img src="https://agentmods.dev/badge/commands/sytungan/emoji-speak/emoji.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 | $0.00018 | $0.00300 |
| Opus 5 | $0.00009 | $0.00150 |
| Sonnet 5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
emoji 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 9d 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.
What it actually says
The user invoked /emoji-speak:emoji with arguments: $ARGUMENTS
Parse the argument:
on→ switch to emoji-speak mode starting with this response.off(or no argument) → switch to normal English mode starting with this response.
Then run one of the following shell commands (using the Bash tool) to persist the choice so the next SessionStart hook honors it:
For on:
mkdir -p "${XDG_CONFIG_HOME:-$HOME/.config}/emoji-speak" && \
printf '{"defaultMode":"on"}\n' > "${XDG_CONFIG_HOME:-$HOME/.config}/emoji-speak/config.json"
For off:
mkdir -p "${XDG_CONFIG_HOME:-$HOME/.config}/emoji-speak" && \
printf '{"defaultMode":"off"}\n' > "${XDG_CONFIG_HOME:-$HOME/.config}/emoji-speak/config.json"
After running the command, acknowledge the mode change.
- If switching to on, the acknowledgement and all subsequent prose must be in 100% emoji per the emoji-speak SKILL (preserve code, paths, URLs, commands, and errors verbatim).
- If switching to off, the acknowledgement is plain English:
emoji-speak off.
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.
- 9d ago First seen · 30 lines · 18 tokens per session scan A 69d4d7f81cce
emoji is a command published in the GitHub repository sytungan/emoji-speak (4 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 300 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
yolo-validate
Run the YOLO change-validation suite — evaluate (4 layers), surface prioritized improvements, optionally apply fixes, then iterate to green. Maintainer tooling; explicit-invoke only.
review
Run full AI code review cycle on current PR branch.
setup
Set up and connect Rami — GitHub App, MCP server, OAuth, and a verification call.
doctor
Diagnose a Rami install — checks auth, GitHub App coverage, quota, and plugin version.
upgrade
Update the Rami plugin to the latest published version and show what changed.
review-status
Check Rami review status without triggering new review.