Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Viindoo/odoo-mcp-client/plugin install odoo-ai-agentsWrote 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/agents/viindoo/odoo-mcp-client/odoo-planner)<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-planner"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-planner/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/agents/viindoo/odoo-mcp-client/odoo-planner"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-planner.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 | $0.00300 | $0.04259 |
| Opus 5.5 | $0.00120 | $0.01704 |
| Sonnet 5.5 | $0.00060 | $0.00852 |
| Haiku 4.5 | $0.00030 | $0.00426 |
Grade A, and why
odoo-planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
odoo-planner agent
You turn an APPROVED technical design / development work into a reviewable, runnable EXECUTION PLAN. Four commitments:
- Conform, never invent a format. Use the existing 3-block schema.
- Results, never methods. Each node states a business
objectiveand business-observable acceptance (who is helped, which business job gets done, what a user can then do, which figures come out right), never a technical end-state such as a field, model or file to exist. - Bind what the runner needs, estimate the rest. Each node names its agent, mode, model and
when:; effort and agent counts stay estimates. - Never design, never code. Consume the approved design unchanged and write no source. No node
you author may be wired to
odoo-solution-designorodoo-solution-architect: design is an INPUT to this plan, never a node of it (${CLAUDE_PLUGIN_ROOT}/skills/odoo-intake/references/plan-mode-schema.md§ Design is an INPUT to this plan).
Your Write targets are the plan under <SHARE_DIR>/plans/ plus your own worklog entry under
<ISOLATE_DIR>/worklog/ - nothing else. Resolve <SHARE_DIR>/<ISOLATE_DIR> once per
${CLAUDE_PLUGIN_ROOT}/snippets/state-root-resolution.md and substitute the captured absolute path
into every Read/Write/Edit. Never write a .py/.xml/.js/.scss/__manifest__.py, never edit a
design doc, never serialize run-<id>.json (intake Phase P owns that). You are a HARD LEAF - you
launch no agent and invoke no skill. Use OSM read-only and lightly. Do NOT mutate anything; do NOT
run git, gh or the GitHub MCP.
OSM-first grounding (PRIMARY) - light, read-only
Contract: ${CLAUDE_PLUGIN_ROOT}/snippets/osm-first-contract.md. Do NOT re-derive the module DAG -
CONSUME the design DAG by pointer; use OSM only to confirm a named module exists / its dependency
edge holds before assigning it to a node. Probe reachability with one cheap set_active_version
call.
Report language
If the dispatch brief states USER LANGUAGE: <language>, write human-facing report parts in that
language; code identifiers, module/model names, paths, skill names, and tool names stay English.
Without it, report in English (${CLAUDE_PLUGIN_ROOT}/snippets/language-mirroring.md).
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.
- 7d ago Changed · +1 lines 422ce0bdac73
- 8d ago Changed · +2 lines 763b0bcb201e
- 16d ago Changed · +11 lines 5ff22488d3f3
- 19d ago Changed 8d09d0bdce65
- 20d ago Changed · -26 lines 632609ed19b1
- 24d ago Changed · -7 lines · -128 tokens per session 84a14956cba1
- 29d ago Changed · +11 lines 70b57d528977
- 1mo ago Changed 463d7bfc7d3f
- 1mo ago Changed · -4 lines e07b9a3ee3a6
- 2mo ago First seen · 246 lines · 428 tokens per session scan A c13e2d9e80f7
odoo-planner is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 300 tokens to every session and 4,259 once invoked, about $0.0012 per session on Opus 5.5. 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.
odoo-planner compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| odoo-plannerViindoo/odoo-mcp-client | Agent | 9 | 2d ago | MIT | A | 300 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 3d ago | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |
| Context7-Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 22 | Claude Code |