Borrowing it
Nothing to install: this file belongs to promptmetrics/hubspot-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/promptmetrics/hubspot-claude/main/AGENTS.mdgit clone --depth 1 https://github.com/promptmetrics/hubspot-claudeWrote 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/promptmetrics/hubspot-claude/agents-md)<a href="https://agentmods.dev/instructions/promptmetrics/hubspot-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/promptmetrics/hubspot-claude/agents-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.
<a href="https://agentmods.dev/instructions/promptmetrics/hubspot-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/promptmetrics/hubspot-claude/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02077 | $0.02077 |
| Opus 5 | $0.01038 | $0.01038 |
| Sonnet 5 | $0.00415 | $0.00415 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
hubspot-claude 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hubspot-claude CLAUDE.md — 95% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents (Claude Code, Codex, etc.) when working with code in this repository.
What This Is
A Claude Code plugin (/hubspot, package hubspot-agent, currently 0.2.14) for natural-language HubSpot CRM administration. Claude orchestrates ~44 specialist sub-agents that each call the hubspot CLI over Bash, with mandatory human-in-the-loop approval for every write. Implementation is complete and actively maintained — this is no longer a greenfield project.
Commands
pip install -e ".[dev]" # editable install with test deps
pytest -x # full suite (~960+ passed, 3 skipped)
pytest tests/test_cli_hitl.py -v # one module
pytest tests/test_safety.py::test_name # one test
claude plugin validate ./ # schema-check plugin.json + marketplace.json + hooks
bash scripts/check-artifact-allowlist.sh # shipping-artifact allowlist gate (run before release)
claude --plugin-dir ./ # load the plugin locally for a session
Tests use pytest-asyncio, respx/pytest-httpx (no live HubSpot calls), and hypothesis (tests/property_based/). tests/conftest.py isolates Path.home() so tests never touch real ~/.claude/hubspot/ state.
Architecture
Claude is the orchestrator; the CLI is the source of truth. There is no custom orchestration framework — Claude Code's native Agent tool spawns stateless sub-agents whose prompts come from hubspot agent-prompt <name>. Sub-agents call ${CLAUDE_PLUGIN_ROOT}/bin/hubspot tool <name> --input '<json>' --portal <id> --working-dir <dir>. --portal/--working-dir are top-level flags and must precede --input.
Three call paths, one handler set. bin/hubspot (POSIX sh venv resolver) → router.py, which prefers the warm-client daemon (daemon.py, Unix-socket JSON-RPC reusing one HubSpotClient + schema cache), falls back to in-process execution, and cli.py also runs sync. All three share handlers.py, so the approve→execute safety contract (destructive-count gate, undo snapshot, created-id capture, audit entry, clear-pending) is identical everywhere. When changing write behavior, change handlers.py/safety.py — never one path.
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.
- 9d ago First seen · 72 lines · 2,077 tokens per session scan A de9e0dd94e23
hubspot-claude AGENTS.md is an instructions file published in the GitHub repository promptmetrics/hubspot-claude (4 stars, last pushed 2d ago), licensed MIT. It adds 2,077 tokens to every session, about $0.0104 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
vscode buildNext.instructions.md
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).
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).
langchain AGENTS.md
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.