Borrowing it
Nothing to install: this file belongs to minhhq-a1/odoo-pulse. 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/minhhq-a1/odoo-pulse/main/CLAUDE.mdgit clone --depth 1 https://github.com/minhhq-a1/odoo-pulseWrote 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/minhhq-a1/odoo-pulse/claude-md)<a href="https://agentmods.dev/instructions/minhhq-a1/odoo-pulse/claude-md"><img src="https://agentmods.dev/badge/instructions/minhhq-a1/odoo-pulse/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.
<a href="https://agentmods.dev/instructions/minhhq-a1/odoo-pulse/claude-md"><img src="https://agentmods.dev/badge/instructions/minhhq-a1/odoo-pulse/claude-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 | $0.01372 | $0.01372 |
| Opus 5 | $0.00686 | $0.00686 |
| Sonnet 5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
odoo-pulse 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 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Install with dev dependencies
pip install -e ".[dev]"
# Run tests (no live Odoo needed)
pytest
# Run a single test file
pytest tests/unit/tools/test_tools_write.py
# Run a single test by name
pytest tests/unit/tools/test_tools_write.py::test_create_record_preview
# Live smoke test against a real Odoo instance (reads only, never writes)
python scripts/smoke/live.py
# Playground: boot a real Odoo in Docker, seed a demo story, assert reports
make playground # boot + seed (follows the seed logs)
make playground-smoke # end-to-end: boot, seed, assert reports, tear down
make playground-reset # wipe the playground (drops the database)
Architecture
This is an MCP server that exposes Odoo's XML-RPC external API as MCP tools. The entry point is src/odoo_pulse/server.py, which calls mcp.registry.load_enabled_modules() to import the tool modules selected by ODOO_TOOL_GROUPS as side effects — each import registers @mcp.tool() (and, for mcp.resources, @mcp.resource()) functions with the shared FastMCP instance.
As of this refactor the package is split into layered subpackages (core, mcp, common, services, tools). All report business logic is consolidated under services/ (report_context.py, pulse.py, crm/, sales/, finance/, hr/, inventory/, operations/, and projects/), while all @mcp.tool() adapters are organized in tools/ (tools/generic.py, tools/writes.py, tools/lists/, tools/reports/).
Module responsibilities:
src/odoo_pulse/core/— config, errors, cache, timeout transports, XML-RPC client, write guardssrc/odoo_pulse/mcp/— FastMCP app, lazy client runtime, JSON result boundary, registry, resource adapter (resources.py)src/odoo_pulse/common/— dates/domains, paging, schema, money, reporting, concurrency; no MCP/global clientsrc/odoo_pulse/services/report_context.py— immutable context (client, today, timezone_offset, company_id) and company domain helpersrc/odoo_pulse/services/records.py— record read service for the MCP resourcesrc/odoo_pulse/services/writes.py— preview shaping, helper values, display-name lookup, and guarded write executionsrc/odoo_pulse/services/pulse.py— cross-department business pulse report orchestrating domain metricssrc/odoo_pulse/services/crm/— CRM metrics (new_leads) and pipeline review servicesrc/odoo_pulse/services/sales/— Sales metrics (confirmed_sales) and sales snapshot servicesrc/odoo_pulse/services/finance/— Finance metrics (overdue_receivables) and receivables health servicesrc/odoo_pulse/services/hr/— HR metrics (employees_off) and absence overview servicesrc/odoo_pulse/services/inventory/— Inventory risk report servicesrc/odoo_pulse/services/operations/— Procurement watch and production health report servicessrc/odoo_pulse/services/projects/— Project queries, subtask metrics, health, finance, budget, profitability, dashboard, workload, standup, and overdue metricssrc/odoo_pulse/tools/— thin decorated adapters (generic.py,writes.py,lists/,reports/)
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 · 71 lines · 1,372 tokens per session scan A b2202a3bf83d
odoo-pulse CLAUDE.md is an instructions file published in the GitHub repository minhhq-a1/odoo-pulse (1 stars, last pushed 20d ago), licensed MIT. It adds 1,372 tokens to every session, about $0.0069 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
agent-skills copilot-instructions.md
Instructions for preset-io/agent-skills: Use the skill files in this package when helping with explicit direct Preset API work. Do not use this package for Preset/Superset MCP tool workflows, and do not switch to direct API calls unless the user explicitly approves changing surfaces.
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.