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/codeforusers/odoo-dev-superskill/xml-ui-behaviorgit clone --depth 1 https://github.com/CodeForUsers/odoo-dev-superskillWhat 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 | $0.00000 | $0.00419 |
| Opus 5 | $0.00000 | $0.00210 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
xml-ui-behavior 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 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.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XML and UI Behavior
Purpose
Define how the agent should behave when working with XML views, XPath inheritance, QWeb, OWL, assets, and Odoo UI-related behavior.
When to activate
- The task modifies XML views.
- The task includes form, list, kanban, search, or calendar views.
- The task uses XPath inheritance.
- The task affects QWeb templates, OWL components, or frontend assets.
- The task touches deprecated UI syntax across versions.
Pre-checks
- Detect Odoo version first.
- Identify whether the change is backend view XML, website QWeb, or OWL/webclient code.
- Check inheritance chains and whether the target element is stable.
- Inspect whether the task modifies list/tree view syntax depending on version.
- Check asset bundle placement and dependency expectations.
Workflow
- Detect version-specific UI syntax requirements.
- Inspect the base inherited view/template before writing XPath.
- Prefer precise and stable XPath targets.
- Keep view changes minimal and localized.
- Separate backend XML, QWeb, and OWL logic conceptually.
- Review whether field visibility rules should live in XML or Python.
- Validate assets and dependencies when frontend code is involved.
- Re-check inheritance robustness after modifications.
Rules
- Never modify XML blindly without understanding inheritance context.
- Use version-correct syntax for list/tree and visibility logic.
- Prefer stable XPath anchors over fragile positional selectors.
- Keep UI logic readable and maintainable.
- Distinguish between presentation logic and business logic.
Avoid
- Fragile XPath expressions tied to positions only.
- Duplicating large inherited views when small XPath patches are enough.
- Mixing QWeb, backend view XML, and OWL concerns without separation.
- Carrying deprecated syntax into newer versions.
- Solving backend problems only in the view layer.
Related references
references/version-matrix.mdreferences/orm-changelog-16-19.mdreferences/security.mdreferences/sql-performance.md
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 First seen · 49 lines · 0 tokens per session scan A bc5710ed1123
xml-ui-behavior is an agent published in the GitHub repository CodeForUsers/odoo-dev-superskill (11 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 419 tokens. 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 2026-08-30.
Other agents, from other repositories
f1-test-drive
Orchestrate F1 test drives to validate the Cyrus agent system end-to-end. Use this agent to run comprehensive test drives that verify issue-tracker, EdgeWorker, and renderer components.
memory
Use when decisions, preferences, or lessons need to persist across sessions - save and retrieve project memory.
debugger
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.
business-estimation-agent
Agent "business-estimation-agent" from girijashankarj/cursor-handbook, covering estimation agent, invocation, scope, expertise and when to use.
team-lead
Sprint phase executor — receives a specific phase (IMPLEMENT/REVIEW/SHIP) and target issues, executes that phase, updates sprint state.
td-hype-synthesizer
You read every 01scout.md file in workspace/hype-scout/, dedupe trends across surfaces, vet each one for buildability in the actual tdmcp codebase (not in the abstract), and produce one prioritized backlog of tdmcp tool ideas that land squarely on what the TouchDesigner community is HYPED about right now.