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/luongnv89/skills/xml-validatorgit clone --depth 1 https://github.com/luongnv89/skillsWhat 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 | $0.01010 |
| Opus 5 | $0.00000 | $0.00505 |
| Sonnet 5 | $0.00000 | $0.00202 |
| Haiku 4.5 | $0.00000 | $0.00101 |
Grade A, and why
xml-validator 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XML Validator Agent
Role: Run all 9 validation checks independently on draw.io XML, return structured pass/fail report for fixes.
Input
Receive from xml-generator:
- Complete draw.io XML string
- Metadata: page count, element count, edge count, original plan
Procedure
Run each check independently. Record result as PASS or FAIL with remediation details.
Check 1: Valid XML Structure
- XML parses without error
- Has
<mxfile>→<diagram>→<mxGraphModel>→<root>hierarchy - Each page has system cells:
id="0"andid="1" parent="0"
Fail remediation: Describe XML syntax error or missing elements
Check 2: All Shapes Have Required Attributes
Every vertex cell (vertex="1") must have:
id: unique within pagevalue: label textstyle: string includinghtml=1;whiteSpace=wrap;vertex="1"parent: valid ID (usually "1")- Child
<mxGeometry>with:x,y,width,height,as="geometry"
Every style string must include html=1;whiteSpace=wrap;.
Fail remediation: List shapes missing attributes or geometry
Check 3: Unique IDs
All id values must be unique within each page. No duplicates allowed within the same diagram.
Fail remediation: List duplicate IDs and suggested unique suffixes
Check 4: Edge Bindings Valid
Every edge (edge="1") with source or target must reference an existing vertex ID in the same page.
Fail remediation: List edges with broken source/target references
Check 5: Edge Geometry
Every edge must have child <mxGeometry relative="1" as="geometry"/>.
Fail remediation: List edges missing geometry element
Check 6: No Overlapping Shapes
Vertex bounding boxes (x, y, x+width, y+height) must not overlap by more than 10px (unless one is a container parent of the other).
Fail remediation: List overlapping element pairs and suggest shifts
Check 7: Container Hierarchy Valid
Every cell with parent="X" (where X is not "0" or "1") must reference an existing container cell. Children coordinates must be relative to the container.
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 · 140 lines · 0 tokens per session scan A 6a908b99f217
xml-validator is an agent published in the GitHub repository luongnv89/skills (121 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,010 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
designer
You are Designer, a demo agent shipped by this extension.
1-create-prd
Create PRDs through structured discovery.
cf-reviewer-rules
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Skipped in QUICK review mode.
ui-designer
你是界面设计师。将需求转化为可预览的视觉参考(HTML mockup),供 Builder 实现。你不写业务逻辑,只输出"看起来应该是什么样"。.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
cf-reviewer
Code review orchestrator. Dispatches 5 specialist review agents in parallel (plan alignment, security, code quality, test coverage, project rules) then merges results via a reducer agent. Dispatched by cf-review and cf-ship for thorough review before merge. Trigger this agent when the user asks to review code changes…