docpull AGENTS.md

Project instructions for DocPull, a tool that collects and manages context for AI agents. It emphasizes local, repeatable, cited results with limits on browsing and spending.

In plain words
What is it for?
Use them when changing DocPull's fetching, caching, citations, browser access, Python package, web package, MCP integration, or validation workflows.
Why use it?
They help keep fetched information traceable and safe while preserving compatibility across the command line, Python library, MCP server, and generated artifacts.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/raintree-technology/docpull/agents-md
Clone the repo
git clone --depth 1 https://github.com/raintree-technology/docpull

Made for: Codex, OpenCode.

Per session 159 This file is loaded in full into every session.
When invoked 159 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00159 $0.00159
Opus 5 $0.00079 $0.00079
Sonnet 5 $0.00032 $0.00032
Haiku 4.5 $0.00016 $0.00016

Measured yesterday against content hash 9e950e1c474c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docpull 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.

AGENTS.md · 15 lines

What it actually says

DocPull Agent Instructions

DocPull is the open-source context dependency manager for AI agents. Its core contract is local-first, browser-free by default, reproducible, cited, and budget guarded.

  • Preserve CLI, Python SDK, MCP, and artifact-contract compatibility.
  • Do not silently enable browser or paid/cloud rendering. Those paths require explicit user configuration and budgets.
  • Respect robots, source rights, provenance, and existing cache/lock semantics.
  • Never store credentials or fetched private content in fixtures or reports.
  • Use uv for Python work and Bun 1.3.11/Node 24 for the web and MCP packages.
  • Run the focused pytest suite while iterating and bun run validate:full from the root for repository-wide changes.
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. yesterday First seen · 15 lines · 159 tokens per session scan A 9e950e1c474c

Subscribe to this mod's changes

docpull AGENTS.md is an instructions file published in the GitHub repository raintree-technology/docpull (25 stars, last pushed 5d ago), licensed MIT. It adds 159 tokens to every session, about $0.0008 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.

Related

Other instructions, from other repositories

markdown_web_browser AGENTS.md

AGENTS.md instructions for Dicklesworthstone/markdown_web_browser, covering agents.md — markdownwebbrowser, rule 0 - the fundamental override prerogative, rule number 1: no file deletion, git branch: only use main, never master and toolchain: python & uv.

Dicklesworthstone/markdown_web_browser · 10,994 tokens

AutomatiQ AGENTS.md

Instructions for StoneSteel27/AutomatiQ, covering agent guidelines, background context, our partner: nodemaven, package structure and important commands.

StoneSteel27/AutomatiQ · 1,669 tokens

webdown CLAUDE.md

Instructions for kelp/webdown, covering webdown development guide, working with claude, version management (semantic versioning), modern python development setup (python 3.10+) and build & testing commands.

kelp/webdown · 1,657 tokens

agentscout AGENTS.md

AGENTS.md instructions for agentx402-ai/agentscout, covering agents.md — agent/contributor guide for this repo, what this repo is, commands, conventions and money-safety invariants (do not weaken).

agentx402-ai/agentscout · 1,472 tokens

agentscout CLAUDE.md

Claude Code instructions for agentx402-ai/agentscout: The shared agent/contributor guide lives in AGENTS.md (cross-tool standard) — commands, conventions, money-safety invariants, release process. Read it first.

agentx402-ai/agentscout · 238 tokens

docs-to-mcp CLAUDE.md

Claude Code instructions for gabrielassisxyz/docs-to-mcp, a project described as: Turn a documentation site into an MCP server your coding agent can search — crawl once with Firecrawl, serve over MCP.

gabrielassisxyz/docs-to-mcp · 50 tokens