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/sumologic/sumologic-documentation/sumo-stylenpx skills add SumoLogic/sumologic-documentation --skill sumo-stylegit clone --depth 1 https://github.com/SumoLogic/sumologic-documentationWhat 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 | $0.00055 | $0.02151 |
| Opus 5 | $0.00028 | $0.01076 |
| Sonnet 5 | $0.00011 | $0.00430 |
| Haiku 4.5 | $0.00006 | $0.00215 |
Grade A, and why
sumo-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 2d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sumo Logic Style Guide
Always fetch before applying rules
Before writing, editing, or auditing any content, fetch both of these pages:
- https://www.sumologic.com/help/docs/contributing/style-guide/
- https://www.sumologic.com/help/docs/contributing/word-list/
Apply the fetched rules. This is a living style guide -- the live pages take precedence over everything below. The rules below are fallback defaults only, for cases where the fetch fails or is unavailable.
Voice and tone
- Address readers as "you". Never "the user" or "one."
- Active voice. "Sumo Logic ingests data" not "data is ingested by Sumo Logic."
- Conversational but professional. Avoid stiff, institutional language.
- 8th-grade reading level for introductory and instructional content.
- No "please" in task directives. "Build the query using..." not "Please build..."
- Use "need to" instead of "must" or "have to."
- Always say "Sumo Logic" (not "Sumo" except in code); "we" is acceptable conversationally.
- Avoid filler adjectives. Cut "very", "best", "simply", "just", "easy", "straightforward."
- Be judicious with "always" and "never".
Contractions
- Common contractions (you'll, they're, we're) are acceptable.
- Negative contractions must be spelled out. "cannot" not "can't", "will not" not "won't", "do not" not "don't."
- Avoid uncommon contractions. "should've", "it'll", "they'd" -- rewrite instead.
Language rules
- No abbreviations. Write "for example" not "e.g.", "that is" not "i.e.", "and so on" not "etc."
- Spell out acronyms on first use in body text: "Application Load Balancer (ALB)"; use ALB after. Do not spell out in headings.
- No gender pronouns unless referring to a specific named person.
- No regional idioms or slang.
- Ampersand (&). Do not use for "and" in prose.
- Numbers. Spell out one through nine; use numerals for 10 and above.
Inclusive language
| Use | Avoid |
|---|---|
| allowlist | whitelist |
| denylist | blacklist |
| placeholder data | dummy data |
| primary / main | master |
| press / click | hit |
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.
- 2d ago First seen · 222 lines · 55 tokens per session scan A d0ff691b84f8
sumo-style is a skill published in the GitHub repository SumoLogic/sumologic-documentation (42 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 2,151 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
gr-readme
🇺🇸 GitHub README Writing System — Craft a README that converts visitors to stars in <3 seconds. Proven structure from AFFiNE's 0→60K star journey: tagline engineering, first-screen law, section-by-section copywriting guide, Claude Code integration section, anti-patterns, and a pre-publish checklist. Use when you…
developer-marketing-playbook
Complete developer marketing playbook covering DevRel programs, documentation as marketing, API developer experience, community building, and hackathon strategy. For dev-tool founders who need to reach engineers. Follow @WeiYipei on X.
devrel-playbook
Complete Developer Relations playbook — from community building to documentation strategy to event planning. Covers Discord/Slack management, conference speaking, hackathon sponsorship, and measuring DevRel ROI. By @WeiYipei.
go-swagger3-docs
Documents existing Go HTTP APIs with go-swagger3 godoc @ annotations and struct tags, then generates OpenAPI 3 specs. Use when the user asks to document an API, add Swagger/OpenAPI comments, generate oas.json/yml, or mentions go-swagger3.
README Writer
Generates a professional, comprehensive README.md for any project from its codebase or description.
repo-audit
Audit a repository or prepare it for an open-source release. Audit mode reports whether the README matches the code and whether stated rules are actually enforced; launch mode walks a repo to release-ready with opt-in checklist packs and README templates. Use when asked to "audit this repo," "is this repo ready to go…