agentmods.dev

interdeep: Instructions file for Claude Code

CLAUDE.md

interdeep CLAUDE.md is an instructions file for Claude Code from mistakeknot/interdeep. It costs 488 tokens per session, scanned A, original, MIT.

A project instruction file for Claude Code, an AI coding assistant. This one documents the interdeep research plugin, its commands, tests, server startup, and main files.

In plain words
What is it for?
Use it as a reference when developing, testing, or starting the interdeep research server.
Why use it?
It gives the coding assistant project-specific guidance so it can work with the repository and run its checks consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is mistakeknot/interdeep's own configuration. It tells Claude Code how to work on interdeep itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything interdeep configures →

not rated 0repo 3mo ago A scan 488 tokens original MIT
View source ↗ mistakeknot/interdeep
Reuse

Borrowing it

Nothing to install: this file belongs to mistakeknot/interdeep. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mistakeknot/interdeep/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mistakeknot/interdeep

Made for: Claude Code.

Wrote 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.

agentmods badge for interdeep CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mistakeknot/interdeep/claude-md/github.svg)](https://agentmods.dev/instructions/mistakeknot/interdeep/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mistakeknot/interdeep/claude-md"><img src="https://agentmods.dev/badge/instructions/mistakeknot/interdeep/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for interdeep CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mistakeknot/interdeep/claude-md"><img src="https://agentmods.dev/badge/instructions/mistakeknot/interdeep/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 488 This file is loaded in full into every session.
When invoked 488 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00488 $0.00488
Opus 5.5 $0.00195 $0.00195
Sonnet 5.5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 2mo ago against content hash ecfc10d858bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

interdeep 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 2mo 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.

CLAUDE.md · 46 lines

What it actually says

interdeep

See AGENTS.md for full development guide.

Overview

Deep research plugin — 4 MCP tools (extract_content, extract_batch, compile_report, research_status), 1 skill (deep-research), 3 agents (research-planner, source-evaluator, report-compiler), 1 command (/research). Python MCP server with trafilatura + optional Playwright extraction. Composes with interject (search), intersynth (synthesis), interknow (knowledge), intercache (caching), interlens (thinking gaps).

Quick Commands

# Run tests
uv run pytest tests/test_extraction.py tests/test_server.py -q

# Run structural tests
cd tests && uv sync && uv run pytest -q && cd ..

# Start MCP server
uv run interdeep-mcp

# Check extraction capability
uv run python -c "from interdeep.extraction.hybrid import extract_hybrid; print(extract_hybrid(html='<p>test</p>', url='https://x.com'))"

Key Files

  • src/interdeep/server.py — MCP server entrypoint (FastMCP, 4 tools)
  • src/interdeep/extraction/ — Content extraction layer
    • models.py — ExtractionResult dataclass
    • trafilatura_ext.py — trafilatura wrapper
    • playwright_ext.py — Playwright fallback (optional)
    • hybrid.py — Router: trafilatura-first, Playwright fallback
  • src/interdeep/reports/markdown.py — Report compilation
  • skills/deep-research/SKILL.md — 5-phase research orchestration protocol
  • agents/ — research-planner, source-evaluator, report-compiler
  • commands/research.md — /research slash command

Design Decisions (Do Not Re-Ask)

  • Plugin owns extraction + orchestration only; search providers are interject's responsibility
  • trafilatura fast path + optional Playwright fallback (graceful degradation)
  • Host-agent-as-brain: MCP tools are stateless, orchestration intelligence lives in SKILL.md
  • GPT-Researcher is inspire + port-partially, not a dependency
  • No LangChain dependency — direct MCP protocol
Changes

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.

  1. 2mo ago First seen · 46 lines · 488 tokens per session scan A ecfc10d858bb

Subscribe to this mod's changes

interdeep CLAUDE.md is an instructions file published in the GitHub repository mistakeknot/interdeep (0 stars, last pushed 3mo ago), licensed MIT. It adds 488 tokens to every session, about $0.0020 per session on Opus 5.5. 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 2026-08-31.

Related

interdeep CLAUDE.md compared with instructions from other repositories

interdeep CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
interdeep CLAUDE.mdmistakeknot/interdeepInstructions file03mo agoMITA488Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode