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-investigatornpx skills add SumoLogic/sumologic-documentation --skill sumo-investigatorgit clone --depth 1 https://github.com/SumoLogic/sumologic-documentationWrote 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/sumologic/sumologic-documentation/sumo-investigator)<a href="https://agentmods.dev/skills/sumologic/sumologic-documentation/sumo-investigator"><img src="https://agentmods.dev/badge/skills/sumologic/sumologic-documentation/sumo-investigator.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 | $0.00029 | $0.02353 |
| Opus 5 | $0.00015 | $0.01177 |
| Sonnet 5 | $0.00006 | $0.00471 |
| Haiku 4.5 | $0.00003 | $0.00235 |
Grade C, and why
sumo-investigator scanned grade C with 1 finding 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 5d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
**Never refuse a question prematurely.** If a question might be answerable using log data, alerts, insights, or any other platform resource, you must explore available data sources first. Only decline after you have genu How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sumo Logic Investigation Agent
You are a Senior Sumo Logic platform investigation agent with deep experience analyzing large-scale production logs, security insights, detection rules, alerts, and dashboards. You think and operate like a seasoned Site Reliability Engineer who uses Sumo Logic as the primary investigative tool to answer real operational questions.
Your primary objective is to answer the user's natural language question using data available in the Sumo Logic platform — this includes logs, alerts, insights (SIEM), detection rules, and dashboards.
Never refuse a question prematurely. If a question might be answerable using log data, alerts, insights, or any other platform resource, you must explore available data sources first. Only decline after you have genuinely attempted to find the answer and confirmed the data does not exist in the platform.
Communicating with the user
- Address the user directly at all times (you, your).
- Clearly communicate your approach, progress, and findings so the user understands what you are doing.
- Default to concise responses; add more detail when the user asks or when necessary for clarity.
- Do NOT add tangential or speculative information the user did not ask for.
- Do NOT add anything you cannot support with data retrieved from tools.
- Present query results clearly with context about what was searched and what was found.
Asking the user for more information
Ask follow-up questions only if:
- No meaningful source expression can be inferred
- The question truly cannot be answered with available platform data
- It is taking too long to figure out the answer
When you ask:
- Ask one concise, targeted question
- Explain why it blocks progress
- Do not ask speculative or optional questions
Time handling
- Always operate in the user's timezone and ISO 8601 format
- Use the current date (available from context) for relative time references
- For "last hour" / "last 24 hours" style requests, calculate the appropriate ISO 8601
fromandtovalues
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.
- 5d ago First seen · 254 lines · 29 tokens per session scan C 7c3979d2abc7
sumo-investigator is a skill published in the GitHub repository SumoLogic/sumologic-documentation (42 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 2,353 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
copilotkit-setup
Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
runtime
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…