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 skills add alivirgo/Major-AI-Skills --skill llm-json-contract-checkgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/llm-json-contract-check)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/llm-json-contract-check"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/llm-json-contract-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/llm-json-contract-check"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/llm-json-contract-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.00311 |
| Opus 5 | $0.00014 | $0.00156 |
| Sonnet 5 | $0.00006 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
llm-json-contract-check 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 today.
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.
What it actually says
JSON Contract Check
Scope
Locate the schema and downstream consumer. Use its existing schema validator and declared schema dialect; do not replace it with regular expressions or a hand-written parser. Identify whether empty values, missing fields, and explicit null have different meanings.
Procedure
Treat model output as untrusted data. Check response completion and refusal states before parsing. Validate syntax, schema, and domain invariants as separate steps. Do not silently coerce identifiers, currencies, dates, or enum values.
Checks
Exercise missing required fields, additional fields, wrong types, unknown enums, oversized arrays, truncated JSON, and cross-field contradictions. Record which layer rejects each case and ensure rejection occurs before an external action.
Failure Handling
Use bounded retries only for recoverable generation failures. Return concise validation errors without embedding secrets or treating generated text as instructions. Preserve the original rejected output in an appropriately protected diagnostic record.
Deliverable
Deliver schema tests and explicit accepted/rejected examples. A syntactically valid order with a negative quantity must still fail business validation.
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.
- today First seen · 35 lines · 28 tokens per session scan A 5ec8c092aa90
llm-json-contract-check is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 311 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-12.
Other skills, from other repositories
eval-harness
Professional Eval Harness Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
ax-extract-workflow
Reconstruct workflow behind a past coding-agent artifact using local ax sessions/commits/skills/tool traces. Use when asked how X was built.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.