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 agentmods add rules/jozobeer/mojiemoji-plugin/mojiemoji-githubgit clone --depth 1 https://github.com/jozobeer/mojiemoji-pluginWrote 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/rules/jozobeer/mojiemoji-plugin/mojiemoji-github)<a href="https://agentmods.dev/rules/jozobeer/mojiemoji-plugin/mojiemoji-github"><img src="https://agentmods.dev/badge/rules/jozobeer/mojiemoji-plugin/mojiemoji-github.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00653 |
| Opus 5 | $0.00000 | $0.00327 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
mojiemoji-github 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 3d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mojiemoji-github (Cursor Rule)
For Japanese GitHub Markdown, Cursor should call the shared mojiemoji core before submitting an issue, PR, review, comment, or release note.
Run the published core before posting:
uvx mojiemoji < body.md > decorated.md
uvx resolves the mojiemoji distribution from PyPI on first use, so no
repository checkout and no manual install are involved. Paste or pipe the
decorated output into the GitHub command. Do not hand-build stamp URLs when
the core can render them.
PR bodies need one check the core does not perform: GitHub can copy the PR body into squash / merge commit messages, and stamps must not leak into commit history. Before decorating a PR body, run
gh api 'repos/{owner}/{repo}' --jq '(.allow_squash_merge and .squash_merge_commit_message == "PR_BODY") or (.allow_merge_commit and .merge_commit_message == "PR_BODY")'
from inside the target repository, and when it prints true, post the PR
body undecorated — only an explicit user request overrides this. Every other
surface (issue body, review body, comment, release note) is decorated
unconditionally.
Every rendered stamp should use /emoji/<encoded-text> with font, color,
animation, background, outline, and outline_width. Inline output
should use background=transparent and outline_width=2.
Recommended values: colors a855f7, 22c55e, f59e0b, 06b6d4,
f472b6; animations bane, bure, kirari, yoko_scroll, zairu.
If a Japanese body is intentionally plain, wrap the plain region with
<!-- mojiemoji:off --> and <!-- mojiemoji:on -->.
Canonical Policies
These policies mirror the canonical skill and are not automated in this harness, so apply them by hand:
- Color-shifting animations (
kira/disco/psycho) must omitoutlineandoutline_width; a fixed-color outline fights the hue cycle. All other animations keep the full six-parameter set. - Skip decoration entirely for English-only bodies and for apology, security, legal, compliance, and acceptance-criteria text.
- Keep shields.io badge rows as the first line of the body; stamps start below them.
- prestamp output is the mechanical first pass (catalog hits only). Add inline decoration for the remaining phrases afterwards, then show the decorated body to the user and get confirmation before posting.
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.
- 3d ago First seen · 67 lines · 0 tokens per session scan A b2f1f6eaac93
mojiemoji-github is a cursor rule published in the GitHub repository jozobeer/mojiemoji-plugin (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 653 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 2026-08-31.
Other cursor rules, from other repositories
finalize-feature
Finalize a feature — create branch, commit, and open PR. Invoke when the user asks to finalize, ship, commit, or create a PR for a feature.
commit-flow
Cursor rule "commit-flow" from xuliang2024/cutcli-cookbook, covering 提交流程, 提交前自检（必跑）, conventional commits, pr 流程 and ci 必过线.
git
Git rules. Conventional commits, atomic staging, no force push.
pn-no-cursor-commit-trailers
Do not add Cursor IDE lines to git commit messages (Made-with, Co-authored-by).
release-commit-analysis-auto
This rule analyzes commits to determine if they should trigger a version bump. It categorizes conventional and non-conventional commits into Features, Bug Fixes, Breaking Changes, Documentation, and Other. It uses intelligent keyword matching for non-conventional commits and analyzes file changes to help categorize…
conventional-commits
Conventional Commits for release-please and PyPI releases.