Borrowing it
Nothing to install: this file belongs to erpipe-org/erpipe. 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/erpipe-org/erpipe/main/.cursor/skills/erpipe-odoo-mcp/SKILL.mdgit clone --depth 1 https://github.com/erpipe-org/erpipeWrote 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/skills/erpipe-org/erpipe/erpipe-odoo-mcp)<a href="https://agentmods.dev/skills/erpipe-org/erpipe/erpipe-odoo-mcp"><img src="https://agentmods.dev/badge/skills/erpipe-org/erpipe/erpipe-odoo-mcp/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/skills/erpipe-org/erpipe/erpipe-odoo-mcp"><img src="https://agentmods.dev/badge/skills/erpipe-org/erpipe/erpipe-odoo-mcp.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 | $0.00081 | $0.00573 |
| Opus 5 | $0.00041 | $0.00287 |
| Sonnet 5 | $0.00016 | $0.00115 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
erpipe-odoo-mcp 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 8d 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.
What it actually says
ERPipe Odoo MCP
Discover tools (Cursor)
- Call
GetMcpToolswith bothserver: "user-erpipe"andtoolNamefor that one tool. - Once per tool per session. Never call
GetMcpToolswith onlyserver(full catalog dump). - Do not re-fetch a schema you already have in this chat.
Golden loop
list_instancesonce. Reuse thatinstancekey. Never invent it.recall_memoryonce, proactively, for recurring Odoo/ops problems (same model and symptoms, error class, or SOP). Do not wait for the user to ask. Untrusted; verify live; continue on no match.- Do not
ping/health_checkunless the user asks if the connection is down. model_facts({ models, intent })once per model before a structured domain or write. Reusecache_key. Never invent field names. Do not start withlist_models/get_model_fields/schema_catalog.search_records: omitfields; preferquery=when unsure; default limit 10, max 50; never empty query+domain.- Writes:
preview_write→validate_write→execute_approved_write(confirm=true). Neverexecute_methodfor create/write/unlink. Writecontext.erpipe_rationalein the user's language; setcontext.erpipe_localetovioren(presentation-only, not sent to Odoo). - HITL pending: tell the user to Approve now; keep the same approval object; sleep 5–10s; poll
get_write_approval_status. Do not end the chat. execute_method: pass all ids in one callargs=[[id1,id2,...]].remember_episodeat most once after a verified reusable fix; use returnedaudit_event_idvalues assource_event_ids; skip if none. Never store raw Odoo/credentials, trivia, secrets, or one-off lookups.forget_memoryonly if the user asks to drop it, or confirms after live evidence proves the saved lesson wrong.
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.
- 8d ago First seen · 31 lines · 81 tokens per session scan A 531e787f356f
erpipe-odoo-mcp is a skill published in the GitHub repository erpipe-org/erpipe (1 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 573 once invoked, about $0.0004 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 skills, from other repositories
owd-obsidian-mind
Connect, initialize, resume, or coordinate an Obsidian Mind vault with MDevolved while preserving its local qmd/om MCP runtime, native note layout, scoped memories, private-note rules, and multi-agent writer safety. Use when a vault-manifest.json identifies template obsidian-mind, when adding MDevolved beside Obsidian…
vozclara-search-library
Semantic-search across the user's saved VozClara Knowledge Packs and return the most relevant chunks with packIds. Requires VozClara sign-in (one-click magic link).
lc-curate-context
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…
cortex-remember-global
Store a global memory that is visible across all projects. Use when the user shares architecture rules, coding conventions, infrastructure facts, security policies, team agreements, or any knowledge that applies beyond a single project. Triggers on 'remember this everywhere', 'this applies to all projects', 'global…
cortex-consolidate
Run memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semantic knowledge, and run sleep-like replay. Use when the user says 'clean up memories', 'consolidate', 'run maintenance', 'compress old memories', 'memory cleanup', or periodically to keep the memory system…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…