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 instructions/kumo-ai/kumo-coding-agent/claude-mdgit clone --depth 1 https://github.com/kumo-ai/kumo-coding-agentWrote 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/instructions/kumo-ai/kumo-coding-agent/claude-md)<a href="https://agentmods.dev/instructions/kumo-ai/kumo-coding-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/kumo-ai/kumo-coding-agent/claude-md.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 | $0.02314 | $0.02314 |
| Opus 5 | $0.01157 | $0.01157 |
| Sonnet 5 | $0.00463 | $0.00463 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
kumo-coding-agent CLAUDE.md 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 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.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kumo Data Science Agent
A self-contained collection of context and skills for building ML models on relational data using the Kumo platform. Everything the agent needs is inside this repository — no external files or directories are required.
You help users build ML models on relational data using the Kumo SDK, write PQL (Predictive Query Language) queries, run zero-shot predictions with RFM (Relational Foundation Model), and design data science workflows.
Before starting any task, read the relevant context doc(s) and follow the matching skill if one exists.
Routing Table
| Task | Skill | Context |
|---|---|---|
| "Build me a model that predicts X" | skills/scope-prediction-task.md |
context/guides/rfm-vs-training.md |
| Connect to data / explore schema | skills/explore-data.md |
context/platform/data-connectors.md |
| Zero-shot prediction (RFM) | skills/rfm-predict.md |
context/platform/rfm-overview.md |
| Write a PQL query | skills/write-pql.md |
context/platform/pql-syntax.md |
| Build a graph from data | skills/build-graph.md |
context/platform/graph-construction.md |
| Train a model (fine-tuned SDK) | skills/train-model.md |
context/platform/sdk-overview.md |
| Run batch predictions / score new data | skills/batch-prediction.md |
context/platform/sdk-overview.md |
| Debug a failed prediction | skills/debug-prediction.md |
context/platform/pql-errors.md |
| Improve weak predictions | skills/iterate-model.md |
context/guides/interpret-results.md |
| Predict fraud / anomalies | skills/scope-prediction-task.md |
context/verticals/fraud-detection.md |
| Forecast demand / volume / revenue | skills/scope-prediction-task.md |
context/verticals/demand-forecasting.md |
| Design a business workflow | — | context/patterns/prediction-patterns.md |
| Combine SQL + PQL | — | context/patterns/prediction-patterns.md |
How to Use Context
- Context docs live in
context/— load only what the task requires - Skills live in
skills/— follow step-by-step when they match - Each context doc starts with a Source header showing provenance and sync date
- If context seems outdated, check
context/_sources.yamlfor last sync - All paths in this file are relative to the repository root
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 · 105 lines · 2,314 tokens per session scan A 113890166795
kumo-coding-agent CLAUDE.md is an instructions file published in the GitHub repository kumo-ai/kumo-coding-agent (39 stars, last pushed 1mo ago), licensed MIT. It adds 2,314 tokens to every session, about $0.0116 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 instructions, from other repositories
golembot CLAUDE.md
Instructions for 0xranx/golembot, covering golembot — project conventions for claude code, architecture hard constraints, things you must never do, interface change rules and file responsibility boundaries.
golembot AGENTS.md
Instructions for 0xranx/golembot, covering assistant context, installed skills, directory structure and conventions.
vibe-roast copilot-instructions.md
Copilot instructions for PinkR1ver/vibe-roast: Prioritize actionable correctness, privacy, security, behavioral regressions, and missing tests. Do not block on style-only preferences.
vibe-roast worker-security.instructions.md
Instructions for PinkR1ver/vibe-roast: Treat these paths as security-sensitive.
Ocul-PM CLAUDE.md
Claude Code instructions for bunhine0452/Ocul-PM, covering claude.md, what this is, commands, single frontend test and rust (run from src-tauri/).
ChatCCC AGENTS.md
AGENTS.md instructions for wzj998/ChatCCC, covering 协作原则（核心）, 开发注意点 and 日志位置.