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/mistakeknot/interdeep/agents-mdgit clone --depth 1 https://github.com/mistakeknot/interdeepWhat 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 | $0.01273 | $0.01273 |
| Opus 5 | $0.00636 | $0.00636 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
interdeep AGENTS.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 yesterday.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
interdeep — Agent Guide
Deep research plugin for Claude Code. Content extraction via trafilatura/Playwright and multi-phase research orchestration via MCP tools, skills, and agents.
Canonical References
PHILOSOPHY.md— direction for ideation and planning decisions.CLAUDE.md— implementation details, architecture, testing, and release workflow.
Execution Rules
- Keep changes small, testable, and reversible.
- Run validation commands from
CLAUDE.mdbefore completion. - Commit only intended files and push before handoff.
Quick Reference
| Item | Value |
|---|---|
| Language | Python 3.12+ |
| Build | hatchling |
| MCP tools | extract_content, extract_batch, compile_report, research_status |
| Skills | deep-research (5-phase orchestration) |
| Agents | research-planner (haiku), source-evaluator (haiku), report-compiler (sonnet) |
| Commands | /research [quick|balanced|deep] <query> |
| Dependencies | trafilatura, aiohttp, mcp, json-repair |
| Optional deps | playwright (browser extraction fallback) |
Overview
interdeep provides two capabilities:
- Content extraction — fetch and clean web content via trafilatura (fast path) with optional Playwright fallback for JavaScript-heavy pages. Exposed as MCP tools for any agent to call.
- Research orchestration — a 5-phase protocol (Orient, Search, Extract, Synthesize, Persist) defined in
SKILL.mdthat composes interdeep's extraction tools with companion plugins for search, synthesis, and knowledge storage.
Architecture
interdeep/
.claude-plugin/
plugin.json # Plugin manifest
src/interdeep/
__init__.py
server.py # FastMCP server — 4 tools
extraction/
__init__.py
models.py # ExtractionResult dataclass
trafilatura_ext.py # trafilatura wrapper
playwright_ext.py # Playwright fallback (optional)
hybrid.py # Router + batch extraction
reports/
__init__.py
markdown.py # Markdown report compiler
skills/
deep-research/
SKILL.md # 5-phase research protocol
agents/
research-planner.md # Query decomposition (haiku)
source-evaluator.md # Source credibility (haiku)
report-compiler.md # Report assembly (sonnet)
commands/
research.md # /research slash command
scripts/
launch-mcp.sh # MCP server launcher
bump-version.sh # Version bump helper
tests/
test_extraction.py # Extraction unit tests
test_server.py # MCP server tool tests
structural/ # Plugin standard structural tests
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.
- yesterday First seen · 134 lines · 1,273 tokens per session scan A 838488a6c05b
interdeep AGENTS.md is an instructions file published in the GitHub repository mistakeknot/interdeep (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,273 tokens to every session, about $0.0064 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.