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 skills/prebid/salesagent/google-stylenpx skills add prebid/salesagent --skill google-stylegit clone --depth 1 https://github.com/prebid/salesagentWrote 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/prebid/salesagent/google-style)<a href="https://agentmods.dev/skills/prebid/salesagent/google-style"><img src="https://agentmods.dev/badge/skills/prebid/salesagent/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 | $0.00072 | $0.03149 |
| Opus 5 | $0.00036 | $0.01574 |
| Sonnet 5 | $0.00014 | $0.00630 |
| Haiku 4.5 | $0.00007 | $0.00315 |
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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Style for Repo Prose
Source: https://developers.google.com/style. Every rule cites the page that mandates it. Where the guide is silent, this file says so — never invent a rule and attribute it to Google. Rules are ordered by how often agent-written prose violates them; rules 1-7 account for most of the damage.
1. Active voice — name the actor
https://developers.google.com/style/voice
Passive voice hides who does the thing, which turns a contract into a rumor.
- Wrong: "The identity is resolved and the request is forwarded to
_impl." - Right: "The MCP wrapper resolves the identity and forwards the request to
_impl."
Passive is allowed in exactly three cases: to emphasize the object ("The file is saved"), to de-emphasize the actor ("Over 50 conflicts were found"), or when the actor is irrelevant ("The database was purged in January").
2. Present tense — drop "will"
https://developers.google.com/style/tense
Use present tense for behavior not tied to a point in time. Reserve "will" for something that genuinely happens later. Never use "would".
- Wrong: "The repository will raise
NotFoundErrorwhen the tenant is missing." - Right: "The repository raises
NotFoundErrorwhen the tenant is missing." - Right (genuinely later): "Add the step to the formula. The atom runs the next time the lane executes."
- Wrong: "You could call the wrapper, and it would then translate the error."
3. Second person — "you", not "we"
https://developers.google.com/style/person
Address the reader as "you". "We" is only for the authoring organization, which has no voice in task descriptions or notes. Imperative is second person with "you" implied — prefer it in steps.
- Wrong: "We then add the guard to the allowlist, and our test catches it."
- Right: "Add the guard to the allowlist. The test catches the violation on the next
make qualityrun."
4. No hedging, no filler, no "easy"
https://developers.google.com/style/tone and https://developers.google.com/style/word-list
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 · 262 lines · 72 tokens per session scan A 4dcb3323434b
google-style is a skill published in the GitHub repository prebid/salesagent (37 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 3,149 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 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…