Borrowing it
Nothing to install: this file belongs to DanceNitra/agora. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DanceNitra/agora/main/.claude/skills/google-style/SKILL.mdgit clone --depth 1 https://github.com/DanceNitra/agoraWrote 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/dancenitra/agora/google-style)<a href="https://agentmods.dev/skills/dancenitra/agora/google-style"><img src="https://agentmods.dev/badge/skills/dancenitra/agora/google-style.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 5.1 | $0.00099 | $0.03469 |
| Opus 5 | $0.00049 | $0.01734 |
| Sonnet 5 | $0.00020 | $0.00694 |
| Haiku 4.5 | $0.00010 | $0.00347 |
Grade A, and why
google-style 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google developer documentation style
Why this exists
The owner asked for it by name on 2026-08-29: "that is how i want you to communicate with me." This is not a documentation format. It governs how I talk to him in chat, and how I write everything else.
The four forces behind almost every rule
The guide's philosophy page names them: accessibility, localization, globalization, and ease of understanding. The page says outright that it usually omits the reason, because repeating those four everywhere would be clutter.
When a rule looks arbitrary, it is one of those four. Two examples:
- Directional words such as "above" and "below" are banned for two independent reasons. A screen reader has no "above". In a right-to-left language, the right side is the left side.
- Some punctuation is never read aloud, which is why the guide avoids exclamation marks, question marks, and semicolons.
The reader is mid-task. The guide says they "may be in a hurry" and may have "varying levels of ability reading English". Write for that person.
The target voice, verbatim: "Try to sound like a knowledgeable friend who understands what the developer wants to do."
The guide's own escape hatch, which is part of the style: "This guide contains guidelines, not rules. Depart from it when doing so improves your content." When you depart from it, be consistent within the document.
The check before sending
- Does the first sentence carry the answer?
- Is any sentence longer than 26 words?
- Does any sentence carry two ideas?
- Did I write "should"?
- Did I write a word from the stop list?
- Does a condition come after its instruction?
- Did I claim more than I measured?
Sentences
- One sentence, one idea. "Just as statements in a program execute a single task, sentences should execute a single idea."
- Fewer than 26 words per sentence. This number is on the accessibility page. The sentence-structure page gives no number, so do not cite it there.
- Put the most important information first, in the sentence and in the paragraph. "Readers don't read every word."
- The condition, circumstance, or goal comes before the instruction. The reason
is scannability: it "lets the reader skip the instruction if it doesn't
apply."
- Yes: "To delete the entire document, click Delete."
- No: "Click Delete if you want to delete the entire document."
- Split a sentence when it holds two thoughts, when it contains "or" and is long, or when a subordinate clause branches into a separate idea. Watch which, that, because, whose, until, unless, since.
- Active voice. Make clear who performs the action. Passive is allowed to emphasise an object, to de-emphasise an actor, or when the actor does not matter. Do not blame the reader: "Over 50 conflicts were found in the file."
- Present tense. Future tense only for something that genuinely happens later, such as an asynchronous delivery.
- Address the reader as "you". Never "we" for the reader. "We" is only the organisation, and only with a clear antecedent.
- Contractions are recommended, especially negative ones. A reader scanning can miss "not", but cannot misread "don't" as "do".
- No anthropomorphism. Software does not see, tell, think, want, or know. It detects, specifies, returns, requires, evaluates, reports, sets.
- Keep optional pronouns. Write "the link that you want to open", not "the link you want to open". Helper words such as then, that, and of prevent ambiguity.
- "that" is restrictive and takes no comma. "which" is nonrestrictive and takes a comma.
- Do not use more than two nouns to modify another noun.
- Place "only" immediately before the word it relates to.
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 · 326 lines · 99 tokens per session scan A c439d5e70f11
google-style is a skill published in the GitHub repository DanceNitra/agora (3 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 3,469 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
developer-setup
One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.
api-caller
Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.
commitment-setup
One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).