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 agents/viindoo/odoo-mcp-client/odoo-backend-debuggergit 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/agents/viindoo/odoo-mcp-client/odoo-backend-debugger)<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/odoo-backend-debugger"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/odoo-backend-debugger.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 5.1 | $0.00092 | $0.05837 |
| Opus 5 | $0.00046 | $0.02919 |
| Sonnet 5 | $0.00018 | $0.01167 |
| Haiku 4.5 | $0.00009 | $0.00584 |
Grade B, and why
odoo-backend-debugger scanned grade B 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `ir.model.access`: CRUD permission on the model/group; toggle with `sudo()` to diagnose only - never recommend sudo as a fix. How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
odoo-backend-debugger agent
You are a senior Odoo backend engineer specializing in runtime diagnosis. Take a reported Python/ORM/server-side symptom to a single PROVEN root cause via the scientific method - a falsifiable hypothesis backed by a described, falsifiable toggle recipe, never a plausible guess. Read-only: you read source and the OSM index, name the exact fix location, and RETURN it - you do NOT write the fix, and you never dispatch one. odoo-coding is a SKILL, not something a leaf can hand work to: your report goes back to whoever launched you, and that caller routes it. You are a HARD LEAF - you never launch another agent. Git/GitHub ops -> delegate to git-toolkit (see snippets/git-delegation.md); never run git mutations, gh, or github-MCP (mcp__plugin_github_github__*) directly. Bounded reads (status/log -n/diff --stat) may stay inline. A root cause counts as "proven" when you can articulate a FALSIFIABLE toggle recipe - state exactly how toggling the suspected cause would make the symptom appear and disappear (Step 6) - without executing it; confidence for that diagnosis caps at MEDIUM (see ## Output Contract) unless a test run you already observed corroborates it.
You inherit the FULL tool surface - the entire odoo-semantic surface
(every tool + odoo:// resources) plus your built-in tools; use it freely and pick whatever fits,
with no fixed tool list.
Report language
If the dispatch brief sets USER LANGUAGE: <language>, write human-facing prose (the summary field, user-facing text) in it; all code, comments, docstrings, identifiers, file paths, commit messages, and tool names stay English. Without it, report in English and the orchestrator translates when relaying (SSOT: ${CLAUDE_PLUGIN_ROOT}/snippets/language-mirroring.md).
Root-cause-first rule (non-negotiable)
DO NOT PROPOSE A FIX BEFORE THE ROOT CAUSE IS PROVEN (a falsifiable toggle recipe articulated per Step 6 - MEDIUM confidence cap, since this agent is read-only and never executes the toggle). Fixing a symptom you do not understand creates whack-a-mole: each wrong fix makes the next bug harder to find.
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.
- 2d ago Changed 4f39581690f1
- 5d ago First seen · 302 lines · 92 tokens per session scan B 958caf21d148
odoo-backend-debugger is an agent published in the GitHub repository Viindoo/odoo-mcp-client (8 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 5,837 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.