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 ShiroRyu9/community-ops-kit --skill community-ops-expressiongit clone --depth 1 https://github.com/ShiroRyu9/community-ops-kitWrote 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/shiroryu9/community-ops-kit/community-ops-expression)<a href="https://agentmods.dev/skills/shiroryu9/community-ops-kit/community-ops-expression"><img src="https://agentmods.dev/badge/skills/shiroryu9/community-ops-kit/community-ops-expression/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/shiroryu9/community-ops-kit/community-ops-expression"><img src="https://agentmods.dev/badge/skills/shiroryu9/community-ops-kit/community-ops-expression.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 | $0.00084 | $0.00904 |
| Opus 5 | $0.00042 | $0.00452 |
| Sonnet 5 | $0.00017 | $0.00181 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
community-ops-expression 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 8d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Community Ops Expression
Overview
Use this skill to make community-ops writing sound like a real operator wrote it: clear, grounded, and easy to act on.
The default process is:
audience -> facts -> action needed -> boundary -> concise wording -> self-check
Project Inputs
Get the source facts, audience, publishing surface, desired reader action, language or voice constraints, and confirmation status of timing, rewards, benefits, metrics, permissions, or official claims from the user or an approved project source.
The skill supplies writing judgment and output patterns. It does not supply project facts, brand voice, activity rules, numbers, approvals, or publication status. Low-risk tone details may be inferred from the request; material facts and sensitive claims may not. Do not reuse example values or present placeholders as finished copy.
First Questions To Resolve Silently
Before writing, infer:
- who will read it: users, creators, paid members, owners, team, recruiters, or public readers;
- what action the reader should take next;
- which facts are confirmed and which are only drafts or ideas;
- whether there is any reward, paid benefit, permission, privacy, safety, or official-claim boundary.
Ask the user only if missing context changes a risky public or official statement.
Writing Rules
Be Concrete
Name the surface, action, and next step:
- where it appears;
- who it is for;
- what the reader should do;
- what proof or response is needed;
- what happens next.
Avoid empty phrases such as "boost engagement", "build an ecosystem", or "increase stickiness" unless paired with a concrete mechanism and measurement.
Keep Operator Voice
Use direct sentences. Prefer practical verbs:
- collect;
- check;
- route;
- remind;
- prepare publication draft;
- review;
- archive;
- follow up;
- compare;
- confirm.
For Chinese outputs, write naturally and avoid over-structured template tone.
For short outputs, preserve the conclusion, supporting evidence, material caveat, and next action. Remove introductions, repetition, generic reassurance, and optional background first. Define tone through observable writing choices instead of broad labels such as "friendly" or "professional".
What ships with it
1 file 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.
- 8d ago First seen · 142 lines · 84 tokens per session scan A ac1dc86ab2f7
community-ops-expression is a skill published in the GitHub repository ShiroRyu9/community-ops-kit (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 904 once invoked, about $0.0004 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 skills, from other repositories
skool-actor
Use this skill when the user wants to read or write to a Skool community programmatically. Triggers on phrases like "list pending Skool members", "post to my Skool community", "approve all pending applicants", "publish a Skool course", "update the Auto DM message", "reply to a comment in Skool", "build a Skool course…
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
x-tweet-by-conversation
Collects every tweet in an X (Twitter) conversation thread given a conversation id (root tweet id) — the focal tweet plus all replies, sub-replies, and quote chains — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, inreplyto mapping, and cursor for pagination. Use…
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.