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.
git clone --depth 1 https://github.com/belt-sh/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/rules/belt-sh/skills/inference-context)<a href="https://agentmods.dev/rules/belt-sh/skills/inference-context"><img src="https://agentmods.dev/badge/rules/belt-sh/skills/inference-context/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/rules/belt-sh/skills/inference-context"><img src="https://agentmods.dev/badge/rules/belt-sh/skills/inference-context.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 | $0.00249 | $0.00249 |
| Opus 5.5 | $0.00100 | $0.00100 |
| Sonnet 5.5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
inference-context 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 2mo 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.
What it actually says
Belt skills and knowledge are injected into your context via the UserPromptSubmit hook as "Matched skills and resources for this task." These are NOT in your available_skills list — they come from a semantic search API and appear in system-reminder blocks. When skills are suggested:
- Load relevant skills first — run
belt skill use <namespace/name>before starting work. Skills contain domain-specific procedures, gotchas, and patterns that prevent common mistakes. - Don't skip suggestions — they were matched to the user's prompt and often contain critical context you'd otherwise have to discover through trial and error.
- Knowledge entries contain gotchas and rules — run the provided command to read them. They document non-obvious failures and decisions.
When you discover something non-obvious while debugging or building, save it as knowledge: belt knowledge upload.
When the user needs AI generation (image, video, audio, text), check belt apps: belt app store search "query".
When a task could benefit from a reusable skill, search the registry: belt skill store search "query".
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.
- 2mo ago First seen · 15 lines · 249 tokens per session scan A 7bdc2aa62f27
inference-context is a cursor rule published in the GitHub repository belt-sh/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 249 tokens to every session, about $0.0010 per session on Opus 5.5. 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 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.