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-generatorsgit 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-generators)<a href="https://agentmods.dev/skills/besser-pearl/besser-skills/besser-generators"><img src="https://agentmods.dev/badge/skills/besser-pearl/besser-skills/besser-generators/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-generators"><img src="https://agentmods.dev/badge/skills/besser-pearl/besser-skills/besser-generators.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 | $0.00246 | $0.02446 |
| Opus 5 | $0.00123 | $0.01223 |
| Sonnet 5 | $0.00049 | $0.00489 |
| Haiku 4.5 | $0.00025 | $0.00245 |
Grade A, and why
besser-generators 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 11d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BESSER Generator Operations
Every BESSER generator implements the same shape:
class GeneratorInterface(ABC):
def __init__(self, model, output_dir=None): ...
def generate(self): ...
If output_dir is omitted, output goes to <cwd>/output/. The directory
is created automatically (os.makedirs(..., exist_ok=True)).
Regeneration always overwrites. Every call to generate() replaces the
output files entirely. This is by design — the model is the source of truth.
Customizations belong in separate files (see "Safe customization" below).
Once you have generated, the besser-user skill's "Verification checklist"
covers what to check next (files exist, syntax parses, it runs).
Generate the baseline, then build on top. The point of these generators is that you don't hand-write the boilerplate. The output is template-based and deterministic — the same model produces the same code on every run — so regenerate the baseline freely (cheap and identical each time) and spend your effort only where the work is actually custom: extending and overriding in separate files so a re-run never clobbers it. Often the generated code is all you need; when it isn't, the "Safe customization" patterns below are how you build on top without fighting regeneration.
Generator picker
Per-generator detail (inputs, outputs, options, templates, gotchas) lives in
references/. Find your target, then read the listed reference:
| Want | Generator | Reference |
|---|---|---|
| Python data classes | PythonGenerator |
python-and-data.md |
| Java classes | JavaGenerator |
python-and-data.md |
| Pydantic models (with optional OCL→validator) | PydanticGenerator |
python-and-data.md |
| JSON Schema (regular or NGSI-LD) | JSONSchemaGenerator |
python-and-data.md |
| JSON data from an ObjectModel (instances) | JSONObjectGenerator |
python-and-data.md |
| RDF Turtle vocabulary | RDFGenerator |
python-and-data.md |
| SQLAlchemy ORM | SQLAlchemyGenerator |
persistence.md |
| Raw SQL DDL | SQLGenerator |
persistence.md |
| Supabase (Postgres + RLS) schema | SupabaseGenerator |
persistence.md |
| FastAPI + ORM + Pydantic stack | BackendGenerator |
api-and-web.md |
| Standalone REST API | RESTAPIGenerator |
api-and-web.md |
| Django project | DjangoGenerator |
api-and-web.md |
| Full-stack web app (React + FastAPI + Docker) | WebAppGenerator |
api-and-web.md |
| Flutter mobile app | FlutterGenerator |
api-and-web.md |
| Conversational agent / chatbot | BAFGenerator |
agents-and-other.md |
| Quantum circuit | QiskitGenerator |
agents-and-other.md |
| Terraform infrastructure | TerraformGenerator |
agents-and-other.md |
| PyTorch / TensorFlow neural net | PytorchGenerator / TFGenerator |
agents-and-other.md |
What ships with it
5 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.
- 11d ago First seen · 244 lines · 246 tokens per session scan A 05e5f77d4031
besser-generators is a skill published in the GitHub repository BESSER-PEARL/BESSER-Skills (8 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 246 tokens to every session and 2,446 once invoked, about $0.0012 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
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.