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/deepnoodle-ai/dive/claude-mdgit clone --depth 1 https://github.com/deepnoodle-ai/diveWrote 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/deepnoodle-ai/dive/claude-md)<a href="https://agentmods.dev/instructions/deepnoodle-ai/dive/claude-md"><img src="https://agentmods.dev/badge/instructions/deepnoodle-ai/dive/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 | $0.01916 | $0.01916 |
| Opus 5 | $0.00958 | $0.00958 |
| Sonnet 5 | $0.00383 | $0.00383 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
dive 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Dive is a Go library for building AI agents and integrating with leading LLMs.
Library-first approach — the CLI in experimental/cmd/dive/ is secondary.
Commands
go test ./...— Run all testscd experimental/cmd/dive && go build— Build the CLI (optional)- Use
github.com/deepnoodle-ai/wonton/assertfor all tests
Architecture
Core Types
- Agent (
agent.go): Created viaNewAgent(AgentOptions), returns*Agent. Manages tool execution and conversation. - Extension (
agent.go):Extensioninterface (Tools,Hooks,Rules) for composable agent capabilities. Set onAgentOptions.Extensions. Extensions provide tools, hooks, and system prompt rules that are merged duringNewAgent. - Session (
dive.go):Sessioninterface (ID,Messages,SaveTurn). Set onAgentOptions.Sessionor per-call viaWithSession. Thesessionpackage providesNew()(in-memory) and store-backed implementations. - LLM (
llm/llm.go):LLMandStreamingLLMinterfaces abstract over providers. - Tool (
tool.go):ToolandTypedTool[T]interfaces.FuncTool[T]()creates tools from functions with auto-generated schemas.Toolsetinterface provides dynamic tool resolution per LLM request. Tool panics are auto-recovered. All toolkit constructors return*dive.TypedToolAdapter[T](satisfiesdive.Tool). - Hooks (
hooks.go):Hooksstruct groups hook slices onAgentOptions. Hook types:SessionStartHook,PreGenerationHook,PostGenerationHook,PreToolUseHook,PostToolUseHook,PostToolUseFailureHook,StopHook,PreIterationHook,OnSuspendHook. All hooks receive*HookContext. PreToolUse hooks can setHookContext.UpdatedInputto rewrite the tool args.SessionStartHookfires once at the start of a fresh conversation (no prior messages, non-resume) and returns a*SessionStartResultto seed it (durable or ephemeral viaPersist). - Tracer (
tracer.go):Tracerinterface for observation (tracing, metrics, audit logging). Three methods (StartAgentRun,StartChat,StartToolCall) return(ctx, span); the agent threads ctx through downstream calls so spans nest naturally.NopTracer(default) andMultiTracerlive in core; the OpenTelemetry adapter isotel.NewTracerin thedive/otelmodule. - Suspend/Resume (
tool.go,response.go,dive.go): A tool can pause the agent mid-turn by returningNewSuspendResult(prompt, metadata)orNewSuspendResultWithReason(prompt, reason, metadata)(setsToolResult.Suspend).SuspendReasonclassifies why:SuspendReasonInput(default) orSuspendReasonAuth.CreateResponsereturns(*Response, nil)withStatus == ResponseStatusSuspendedandResponse.Suspension *SuspensionState. Resume viaWithToolResults(session-backed) orWithResume(state, results)(stateless).SuspendableSessionis an optionalSessionextension for auto-persistence withCancelSuspension(ctx)to abandon a suspended turn.OnSuspendhooks fire before persistence. Seedocs/guides/suspend-resume.md.
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 · 93 lines · 1,916 tokens per session scan A 4c597bff0109
dive CLAUDE.md is an instructions file published in the GitHub repository deepnoodle-ai/dive (133 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,916 tokens to every session, about $0.0096 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
memory CLAUDE.md
Instructions for RLabs-Inc/memory, covering memory system - claude.md, project overview, core philosophy, architecture overview and development setup.
claude-code-tamagotchi CLAUDE.md
Instructions for Ido-Levi/claude-code-tamagotchi, covering claude.md, essential commands, development, run the pet in statusline mode (main entry point) and development mode with auto-reload.
tree-sitter-analyzer CLAUDE.md
Claude Code instructions for aimasteracc/tree-sitter-analyzer, covering ruflo — claude code configuration, rules, test quality rules — locked (2026-06-28), t-1: no new test files for existing plugins (blocker) and t-2: no weak assertions — ratchet-enforced (blocker).
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
claude-sessions CLAUDE.md
Instructions for gapmiss/claude-sessions, covering claude sessions — obsidian plugin, development, file structure, code exploration (cymbal) and conventions.