Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/viindoo/odoo-mcp-client/odoo-codingnpx skills add Viindoo/odoo-mcp-client --skill odoo-codinggit clone --depth 1 https://github.com/Viindoo/odoo-mcp-clientWrote 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/viindoo/odoo-mcp-client/odoo-coding)<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-coding"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-coding.svg" alt="Measured on agentmods" 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 | $0.00252 | $0.16684 |
| Opus 5 | $0.00126 | $0.08342 |
| Sonnet 5 | $0.00050 | $0.03337 |
| Haiku 4.5 | $0.00025 | $0.01668 |
Grade C, and why
odoo-coding scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`find <ISOLATE_DIR>/coding/ -mindepth 1 -maxdepth 1 -type d -mmin +43200 -exec rm -rf {} +` How it starts
The opening of the file, as written. The whole thing — 806 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Developer - full-stack Odoo coder (all versions, v8 onward). Orchestrates by WORK NODE: for each
node in the plan (or self-derived when standalone) it resolves the node's module set and
dependency order, assigns a model tier, and dispatches ONE odoo-coder COORDINATOR per node
(every node - backend-only, frontend-only, or full-stack; a node may name one module, part of one,
or several). The odoo-coder coordinator owns the node's INTERNAL work-item (WI) breakdown: for
its ONE node it splits the changes into 1..N WIs by DISJOINT file sets, schedules INDEPENDENT WIs
in PARALLEL and DEPENDENT WIs SEQUENTIALLY (a frontend WI that binds a backend WI runs after it -
the backend-before-frontend order), assigns each WI to the right worker (backend files ->
odoo-backend-coder, frontend files -> odoo-frontend-coder), and owns the integrated whole-node
test on ONE instance. This skill does NOT split a node into WIs and does NOT sequence
backend/frontend - that is odoo-coder's job (SSOT for the two-tier axis:
${CLAUDE_PLUGIN_ROOT}/skills/_shared/odoo-module-graph.md § Two-tier decomposition axis - the
OUTER unit here is the NODE, the WI is odoo-coder's INTERNAL unit; the MODULE is a property of a
node, never the unit of dispatch).
Pair-works with odoo-code-review for review.
Sole dispatcher (single source of truth for coding fan-out). This skill is the ONLY component
that computes the node dependency order + the model tier and launches the odoo-coder
coordinator (one per node). Any other skill that needs Odoo code written routes its coding work
HERE via the Skill tool (passing its context in the brief) instead of launching the coder agents
itself. The intra-node WI split + the backend-before-frontend order are owned by the odoo-coder
coordinator, not here.
Out of Scope
- Reviewing / auditing existing code (not writing) →
odoo-code-review - Locating where to hook into core logic (one method) →
odoo-override-finding - Deprecation analysis / upgrade planning →
odoo-deprecation-audit/odoo-version-diff - Designing the approach before any code (non-trivial) →
odoo-solution-design - Verifying the rendered UI / a runtime render error / image regression →
odoo-ui-review/odoo-debug/odoo-visual-regression
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +11 lines 17934eaa827c
- 5d ago First seen · 795 lines · 252 tokens per session scan C eb03643ee58b
odoo-coding is a skill published in the GitHub repository Viindoo/odoo-mcp-client (8 stars, last pushed 2d ago), licensed MIT. It adds 252 tokens to every session and 16,684 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…