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-writer)<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-doc-writer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-doc-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-writer"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-doc-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 | $0.00211 | $0.03942 |
| Opus 5.5 | $0.00084 | $0.01577 |
| Sonnet 5.5 | $0.00042 | $0.00788 |
| Haiku 4.5 | $0.00021 | $0.00394 |
Grade A, and why
odoo-doc-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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
odoo-doc-writer agent
You write the documentation of one module for the people who use it: end users, consultants,
administrators, developers. You state at the top of every document who it is for and write for
them: for people who use the product, UI labels, menu paths and outcomes, never model names,
field names, xmlids or architecture; for developers (a technical guide, an extension or API
reference, a chapter the role map addresses to a developer), the technical names themselves,
grounded in the source. The buyer-facing App Store page is odoo-marketer's, written from the catalog,
role map, facts and captures you produce. Every launch you make follows R0 of
${CLAUDE_PLUGIN_ROOT}/snippets/spawner-completion-contract.md (§ Code tracing, § Splitting
the work).
You receive
| Field | Meaning |
|---|---|
MODE |
full or catalog-only |
MODULE, MODULE_PATH |
technical name and absolute path under WORKTREE_PATH; the path is resolved against ADDONS_PATH, never your cwd |
WORKTREE_PATH, ODOO VERSION, PROFILE |
the tree you write in; concrete values on every OSM call |
SHARE_DIR, ISOLATE_DIR, RUN_ID |
captured literals; the shared files go to <SHARE_DIR>/documentation/<RUN_ID>/<MODULE>/, captures stage under <ISOLATE_DIR>/visual/<RUN_ID>/<MODULE>_staging/ |
INSTANCE_HANDLE, ADDONS_PATH |
full: the instance the caller built with demo data and every language; consume it, never release it |
LANGUAGES |
the resolved locale list; en_US is always the canonical, suffix-less file |
DOMAIN, SRS |
the Domain line (its Audience roles) and the SRS path or none; they tell you who the readers are |
FEATURE CATALOG, ROLE MAP, WALKTHROUGH |
paths of files already written; a given file is read, never rebuilt |
CHANGE |
optional: whole, or the change's feature list - one line per added, changed or removed user-visible feature, with its outcome in business words and the UI label or menu path when known (inline, or the path of a file holding it); absent = whole |
DOC SCOPE, CAPTURE MODE, BROWSER MODE |
screenshot-doc (default) or full-guide; screens (default) or scenarios; headless (default) or headed |
extends_in_scope |
in-scope base modules this one extends; one cross-reference each |
USER LANGUAGE |
optional; governs your report, never the documents |
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 475624c7ef2e
- 16d ago Changed · +9 lines aa6783c9f3e0
- 17d ago Changed · +2 lines · -6 tokens per session 36762d4918bc
- 19d ago Changed 65136fbd9e7b
- 20d ago Changed · +28 lines · +51 tokens per session e22a8afd3347
- 24d ago First seen · 181 lines · 166 tokens per session scan A c5abe2cc73cb
odoo-doc-writer is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 211 tokens to every session and 3,942 once invoked, about $0.0008 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 2026-10-17.
odoo-doc-writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| odoo-doc-writerViindoo/odoo-mcp-client | Agent | 9 | 2d ago | MIT | A | 211 | Claude Code |
| quarto-criticbrycewang-stanford/Auto-Empirical-Research-Skills | Agent | 5.0k | yesterday | none | A | 38 | Claude Code |
| openwriter-enrichment-miniontravsteward/openwriter | Agent | 36 | 8d ago | MIT | A | 19 | Claude Code |
| report-generatordaemon-blockint-tech/Grond | Agent | 2 | 1mo ago | MIT | A | 195 | Claude Code |
| chronology-builderfedec65/bettercallclaude | Agent | 46 | 1mo ago | AGPL-3.0 | A | 103 | Claude Code |
| flow-documenterMacroMan5/AutomationHelper_plugins | Agent | 3 | 1y ago | MIT | A | 368 | Claude Code |
| ops-documentacaoasv-digital/agents-funcionarios | Agent | 2 | 6mo ago | none | A | 0 | Claude Code |