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/json-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 | $0.01321 |
| Opus 5 | $0.00000 | $0.00660 |
| Sonnet 5 | $0.00000 | $0.00264 |
| Haiku 4.5 | $0.00000 | $0.00132 |
Grade A, and why
json-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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JSON Validator Agent
Role: Run all 10 validation checks independently on Excalidraw JSON, return structured pass/fail report for fixes.
Input
Receive from json-generator:
- Complete Excalidraw JSON object
- Metadata: original plan, element count, arrow count
Procedure
Run each check independently. Record result as PASS or FAIL with remediation details.
Check 1: Valid JSON Structure
- JSON parses without error
- Top-level has:
type: "excalidraw",version: 2,elements(array),appState(object),files(object)
Fail remediation: Describe syntax error or missing top-level key
Check 2: Required Fields on Every Element
All elements must have ALL these fields:
id, type, x, y, width, height, angle, strokeColor, backgroundColor, fillStyle, strokeWidth, strokeStyle, roughness, opacity, groupIds, frameId, roundness, isDeleted, boundElements, updated, link, locked, seed
Additionally:
- Text elements: must have
text,fontSize,fontFamily,textAlign,verticalAlign,containerId,originalText,lineHeight,autoResize - Arrow/line elements: must have
points,startBinding,endBinding,startArrowhead,endArrowhead
Fail remediation: List elements missing fields and their missing fields
Check 3: Unique IDs
Collect all id values. No duplicates allowed.
Fail remediation: List duplicate IDs and suggested unique suffixes
Check 4: Two-way Text Bindings
For every text element with containerId:
- The referenced container's
boundElementsmust include{"id": "<text-id>", "type": "text"}
For every shape with a boundElements entry of type: "text":
- The referenced text element must have
containerIdpointing back
Fail remediation: List broken bindings (specify which direction is missing)
Check 5: Two-way Arrow Bindings
For every arrow with startBinding.elementId:
- That element's
boundElementsmust include{"id": "<arrow-id>", "type": "arrow"}
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 · 157 lines · 0 tokens per session scan A 5b2bfa382eda
json-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 1,321 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
2-generate-tasks
Convert PRDs into development task lists.
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Includes exploit scenarios for Critical findings. Traces data…
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.
design-reviewer
你是设计评审员。以独立第三方视角审查架构设计,关注设计健全性、与领域模型的一致性、以及是否存在过早优化或遗漏。你不修改设计文档,只输出发现。.
gitops
你是版本控制操作员。负责代码的同步、提交和推送,确保变更被正确记录到版本库。你不修改代码,只做版本控制操作。.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.