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 skills/daeryundf2-prog/lazyantigravity/programmingnpx skills add daeryundf2-prog/LAZYANTIGRAVITY --skill programminggit clone --depth 1 https://github.com/daeryundf2-prog/LAZYANTIGRAVITYWrote 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/daeryundf2-prog/lazyantigravity/programming)<a href="https://agentmods.dev/skills/daeryundf2-prog/lazyantigravity/programming"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/programming.svg" alt="Measured on agentmods" 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 | $0.00261 | $0.01387 |
| Opus 5 | $0.00130 | $0.00694 |
| Sonnet 5 | $0.00052 | $0.00277 |
| Haiku 4.5 | $0.00026 | $0.00139 |
Grade A, and why
programming 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 5d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/go/backend-stack.md 17 KB
- references/go/bootstrap.md 8.8 KB
- references/go/bubbletea-v2.md 11 KB
- references/go/cobra-stack.md 12 KB
- references/go/concurrency.md 11 KB
- references/go/data-modeling.md 12 KB
- references/go/error-handling.md 10 KB
- references/go/golangci-strict.md 10 KB
- references/go/grpc-connect.md 10 KB
- references/go/libraries.md 14 KB
- references/go/one-liners.md 5.5 KB
- references/go/README.md 7.4 KB
- references/go/sqlc-pgx.md 13 KB
- references/go/testing.md 14 KB
- references/go/type-patterns.md 9.5 KB
- references/python/async-anyio.md 14 KB
- references/python/data-modeling.md 6.6 KB
- references/python/data-processing.md 4.2 KB
- references/python/error-handling.md 6.0 KB
- references/python/fastapi-stack.md 9.2 KB
- references/python/httpx2-optimization.md 12 KB
- references/python/libraries.md 11 KB
- references/python/one-liners.md 7.8 KB
- references/python/orjson-stack.md 13 KB
- references/python/pydantic-ai.md 8.2 KB
- references/python/pyproject-strict.md 9.0 KB
- references/python/README.md 15 KB
- references/python/textual-tui.md 5.1 KB
- references/python/type-patterns.md 4.1 KB
- references/rust-ub/miri-sanitizers-loom.md 11 KB
- references/rust-ub/README.md 9.7 KB
- references/rust-ub/ub-taxonomy.md 13 KB
- references/rust/async-tokio.md 9.7 KB
- references/rust/axum-stack.md 15 KB
- references/rust/cargo-strict.md 7.5 KB
- references/rust/clap-stack.md 12 KB
- references/rust/concurrency.md 13 KB
- references/rust/libraries.md 14 KB
- references/rust/one-liners.md 7.4 KB
- references/rust/proptest-insta.md 13 KB
- references/rust/README.md 14 KB
- references/rust/type-state.md 11 KB
- references/rust/unsafe-discipline.md 11 KB
- references/rust/zero-cost-safety.md 15 KB
- references/typescript/backend-hono.md 21 KB
- references/typescript/bootstrap.md 7.0 KB
- references/typescript/data-modeling.md 5.0 KB
- references/typescript/error-handling.md 4.7 KB
- references/typescript/README.md 9.3 KB
- references/typescript/threejs-r3f.md 4.3 KB
- references/typescript/tsconfig-strict.md 4.8 KB
- references/typescript/type-patterns.md 5.2 KB
- scripts/go/check-no-excuse-rules.sh 7.1 KB runs code
- scripts/go/new-project.py 4.4 KB runs code
- scripts/go/templates/.editorconfig 206 B
- scripts/go/templates/.golangci.yml 1.5 KB
- scripts/go/templates/AGENTS.md.tmpl 845 B
- scripts/go/templates/ci.yml 863 B
- scripts/go/templates/config.go 643 B
- scripts/go/templates/gitignore 99 B
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.
- 5d ago First seen · 80 lines · 261 tokens per session scan A 024c9c98f11a
programming is a skill published in the GitHub repository daeryundf2-prog/LAZYANTIGRAVITY (14 stars, last pushed today), with no licence file. It adds 261 tokens to every session and 1,387 once invoked, about $0.0013 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 2026-08-30.
Other skills, from other repositories
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
python-testing
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
nodejs-keccak256
Prevent Ethereum hashing bugs in JavaScript and TypeScript. Node's sha3-256 is NIST SHA3, not Ethereum Keccak-256, and silently breaks selectors, signatures, storage slots, and address derivation.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
nestjs-patterns
NestJS architecture patterns for modules, controllers, providers, DTO validation, guards, interceptors, config, and production-grade TypeScript backends.
bun-runtime
Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.