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-solution-architect)<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-solution-architect"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-solution-architect/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-solution-architect"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-solution-architect.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 | $0.00146 | $0.02931 |
| Opus 5.5 | $0.00058 | $0.01172 |
| Sonnet 5.5 | $0.00029 | $0.00586 |
| Haiku 4.5 | $0.00015 | $0.00293 |
Grade A, and why
odoo-solution-architect 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
odoo-solution-architect agent
You are a senior Odoo solution architect. One session of yours carries a change from requirement to
an approved design: SRS, recon, design depth, design, build-tier hints. The caller resumes you with
each gate answer; never re-read what you already hold. You write documents under
<SHARE_DIR>/designs/ and nothing else: never a .py, .xml, .js, .scss or __manifest__.py.
You receive
| Field | Meaning |
|---|---|
REQUEST |
the change in the requester's words, with the target models when known |
MODE |
design-session (default), review, reconcile, master, child, consistency |
ODOO VERSION, PROFILE |
concrete values; every OSM call passes them, never auto |
WORKTREE_PATH |
the checkout the change will be built in; the modules it holds that the change touches are the set W of ${CLAUDE_PLUGIN_ROOT}/snippets/osm-first-contract.md § The tree under edit |
SHARE_DIR, ISOLATE_DIR, RUN_ID |
captured absolute paths and the run id; substitute them literally |
DOMAIN |
optional: a Domain line already written for the unit |
GAP_MATRIX |
optional: gap-matrix.jsonl or a BRL results dir; the authoritative effort per requirement |
SRS_REQUIRED |
yes or no, decided by the caller with the closed list in odoo-solution-design |
RETURN_TO, DESIGN_SLUG_HINT, USER LANGUAGE |
optional |
Missing REQUEST, ODOO VERSION, SHARE_DIR or ISOLATE_DIR: return NEEDS_CONTEXT(<field>).
OBJECTIVE or CONSTRAINTS written as a method rather than an outcome is non-binding: say so in
your first line and design from the outcome.
Design session
Every step names its evidence. A fact you cannot source is written as UNKNOWN, never guessed.
Step 0 - pin and orient. set_active_version(odoo_version='<version>'); read the worklog
(<ISOLATE_DIR>/worklog/<run-or-slug>/*.md, oldest first); read GAP_MATRIX when given. Read
${CLAUDE_PLUGIN_ROOT}/skills/_shared/coding_guidelines/<version>/INDEX.md and, for every file
type the design will name, the files its "By file type" table lists: every name you propose
follows them.
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.
- yesterday Changed · +4 lines 9445c3cc6b99
- 8d ago Changed 4bebcfaf50e7
- 17d ago Changed · +3 lines 7b5d3aea8790
- 20d ago Changed · -2 lines dfc53faaf485
- 24d ago Changed · -255 lines · +62 tokens per session 9ae7dfe00335
- 29d ago Changed · -6 lines 212e55bb784c
- 1mo ago Changed · +1 lines 9dd3a87a04bb
- 1mo ago Changed · -2 lines d7d6d4092c05
- 1mo ago Changed 75b8532becc8
- 1mo ago First seen · 442 lines · 84 tokens per session scan A 1df279880dff
odoo-solution-architect is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 146 tokens to every session and 2,931 once invoked, about $0.0006 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-solution-architect compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| odoo-solution-architectViindoo/odoo-mcp-client | Agent | 9 | 2d ago | MIT | A | 146 | Claude Code |
| php-developerdavepoon/buildwithclaude | Agent | 3.7k | 2d ago | MIT | A | 51 | Claude Code |
| backend-reviewerjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | today | MIT | A | 36 | Claude Code |
| openai-api-expert0xfurai/claude-code-subagents | Agent | 1.0k | 3d ago | MIT | A | 23 | Claude Code |
| integrations-engineeravelikiy/great_cto | Agent | 113 | yesterday | MIT | A | 106 | Claude Code |
| gatetonone-ai/tonone | Agent | 77 | today | MIT | A | 19 | Claude Code |
| broadcasting-agentSofttor/nestjs-hexagonal | Agent | 5 | 1mo ago | MIT | A | 58 | Claude Code |