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 BESSER-PEARL/BESSER-Skills --skill besser-devgit clone --depth 1 https://github.com/BESSER-PEARL/BESSER-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/besser-pearl/besser-skills/besser-dev)<a href="https://agentmods.dev/skills/besser-pearl/besser-skills/besser-dev"><img src="https://agentmods.dev/badge/skills/besser-pearl/besser-skills/besser-dev/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/besser-pearl/besser-skills/besser-dev"><img src="https://agentmods.dev/badge/skills/besser-pearl/besser-skills/besser-dev.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 | $0.00250 | $0.00981 |
| Opus 5 | $0.00125 | $0.00491 |
| Sonnet 5 | $0.00050 | $0.00196 |
| Haiku 4.5 | $0.00025 | $0.00098 |
Grade A, and why
besser-dev 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 12d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to BESSER
This skill covers the procedural workflows for contributing to the BESSER
codebase. For architecture details and code conventions, also consult the
BESSER repo's CLAUDE.md (auto-loaded in Claude Code; with other agents,
read CLAUDE.md at the repo root directly).
Development Setup
git clone https://github.com/<your-username>/BESSER.git
cd BESSER
python -m venv venv
# Windows: venv\Scripts\activate
# macOS/Linux: source venv/bin/activate
pip install -r requirements.txt
pip install -r docs/requirements.txt # for building docs
pip install -e . # editable install
Verify: python tests/BUML/metamodel/structural/library/library.py
Python 3.11+ is required (enforced by python_requires = >=3.11 in
setup.cfg; CI tests 3.11 and 3.12).
Reference layout
This skill keeps SKILL.md short. Reach into references/ for the procedure
you need:
| Task | Read |
|---|---|
| Add a new generator (the most common contribution) — 6 steps + scaffold | references/adding-a-generator.md |
| Add a new metamodel / sub-DSL, plus JSON↔BUML converters | references/adding-a-metamodel.md |
Write pytest tests (fixtures, tmp_path, what to assert) |
references/testing.md |
| Build the Sphinx docs and cross-reference them | references/docs-and-build.md |
| Code style, commit/PR conventions, cross-repo, CI/release | references/contributing-workflow.md |
Related skills for the using side (not contributing):
- Running or customizing an existing generator → the besser-generators skill.
- Diagnosing install/import/generation errors → the besser-troubleshooting skill.
- The user-facing shape of a model type (doc templates) → the besser-user skill's
references/.
Common Contribution Pitfalls
- Don't duplicate logic — shared helpers go in
besser/utilities/, not in individual generators. - Maintain determinism — generators must produce identical output for identical input.
- Keep converters symmetric — if
JSON → BUMLsupports a feature,BUML → JSONmust too. - Update docs — any backend change likely needs
docs/source/updates. - Don't touch the frontend submodule unless explicitly required. UI changes go to the upstream WME repo.
- Clean up resources — always use
try/finallyfor temp directories and file handles. - Test round-trips — especially for converters (
JSON → BUML → JSONshould be identity).
What ships with it
6 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.
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.
- 12d ago First seen · 90 lines · 250 tokens per session scan A 608b04db9ca8
besser-dev is a skill published in the GitHub repository BESSER-PEARL/BESSER-Skills (8 stars, last pushed today), licensed Apache-2.0. It adds 250 tokens to every session and 981 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 2026-08-31.
Other skills, from other repositories
accelerate
Run PyTorch training across GPUs with minimal changes.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
fastapi-templates
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
test-generator
Generate pytest test cases for Python functions and classes.
agenthub-python
Guidance for using the AgentHub Python SDK (agenthub-python). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention AgentHub, request agenthub-python, or already import it.