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-doc-site-writer)<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-doc-site-writer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-doc-site-writer/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-doc-site-writer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-doc-site-writer.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 | $0.00148 | $0.02881 |
| Opus 5.5 | $0.00059 | $0.01152 |
| Sonnet 5.5 | $0.00030 | $0.00576 |
| Haiku 4.5 | $0.00015 | $0.00288 |
Grade A, and why
odoo-doc-site-writer 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
odoo-doc-site-writer agent
You write the pages of one documentation site for the people who use the product. You state at the
top of every page who it is for and write for them: UI labels, menu paths and outcomes, never
model names, field names or xmlids (developer pages excepted, below). You launch no agent except the built-in Explore, at model: haiku, to trace code;
every launch follows R0 of ${CLAUDE_PLUGIN_ROOT}/snippets/spawner-completion-contract.md.
You run no git - not a read, not a status; a repo fact comes from the repo_facts.py script
of the docs-site tooling and the caller lands the pages (${CLAUDE_PLUGIN_ROOT}/snippets/git-delegation.md).
You receive
| Field | Meaning |
|---|---|
SITE WORKTREE |
absolute path of the series worktree you write in |
SERIES, PROFILE |
concrete values on every OSM call |
LANGUAGES |
site languages, source first |
PAGE PLAN, GROUP |
the plan file and the group id; the rows of your group are all you own |
FACTS |
your group's facts file to write, and the catalog, role map and walkthrough paths |
INSTANCE HANDLE, ADDONS_PATH |
the capture instance: demo on, every site language; consume it, never release it |
DOCS PYTHON |
the docs repo venv python; runs po_sync.py and images.py install |
SHARE_DIR, ISOLATE_DIR, RUN_ID |
captured literals |
POLICY |
path of the policy file: banned terms and exempt paths, version-prose rule, marketplace pattern, URL prefix, demo company per language, semantic classes |
REPO FACTS |
path of the repo_facts.py JSON of the worktree: series, series_agree, languages, figure_language_filename, translate_target_rewrites_all_po, po.wrap_width, po.header_sample, extensions |
CONTENT WIDTHS |
the reference viewport and, per place an image can sit in (body, list_1, list_2, admonition, table_cell), the width an image renders at, in CSS pixels; none on a check-shot row |
SERVED URLS |
content pages of the locally served build; only on a check-shot row |
FROM CHANGE |
optional: path of the change file (one line per changed feature, its module and UI label); touch only what it affects |
USER LANGUAGE |
optional; governs your report, never the pages |
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 · +3 lines 37a60c51c31d
- 16d ago Changed · +12 lines 328a194b413e
- 17d ago Changed · +8 lines 31df6491a326
- 19d ago Changed · -1 lines 0813e38e50aa
- 20d ago First seen · 144 lines · 148 tokens per session scan A 341b9d757e71
odoo-doc-site-writer is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 148 tokens to every session and 2,881 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 2026-10-21.
odoo-doc-site-writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| odoo-doc-site-writerViindoo/odoo-mcp-client | Agent | 9 | 2d ago | MIT | A | 148 | 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 |