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-usergit 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-user)<a href="https://agentmods.dev/skills/besser-pearl/besser-skills/besser-user"><img src="https://agentmods.dev/badge/skills/besser-pearl/besser-skills/besser-user/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-user"><img src="https://agentmods.dev/badge/skills/besser-pearl/besser-skills/besser-user.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 | $0.00343 | $0.03237 |
| Opus 5 | $0.00171 | $0.01618 |
| Sonnet 5 | $0.00069 | $0.00647 |
| Haiku 4.5 | $0.00034 | $0.00324 |
Grade A, and why
besser-user 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.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with BESSER
BESSER is a model-driven platform: describe your domain as a model, then generators turn that model into running code. The model is the source of truth — when requirements change, update the model and regenerate. Never hand-edit generated code as your primary change.
Core workflow
1. Define requirements
2. Build a B-UML model (Python API, PlantUML, or web editor)
3. Validate the model: model.validate()
4. Pick a generator for your target platform
5. Generate code
6. Verify the output (run, test, inspect)
7. Iterate: update the model, regenerate
Two outcomes: code or documentation
A B-UML model is useful even if you never run a generator. Feed it to a
generator for code, or embed it in a README/design doc as a correct,
validate()-checked class diagram that documents any project. So
reach for this skill whenever you need an accurate class diagram — not only
when the project will use BESSER's generators.
Deliver it accordingly: default to a runnable .py file, or embed the same
B-UML in Markdown when the request is documentation-oriented. For the full
how-to — making the file self-contained, and the two ways the user runs or
imports it — see references/delivering-models.md.
Don't deliver the diagram as a Mermaid block. This skill exists so the diagram is a real,
validate()-checked B-UML model — not a throwaway```mermaid classDiagram```that drifts from the code. When asked for a class diagram, the deliverable is B-UML (the.pymodel and/or the same model embedded in Markdown); when a rendered image is wanted, produce an SVG/PNG from the B-UML — one call to BESSER's headlessB-UML → SVGendpoint (POST https://editor.besser-pearl.org/besser_api/get-svg, send the.py), or Import → B-UML in the web editor, then export. A quick ASCII sketch is fine as an inline preview, but the authoritative artifact is always the B-UML model — not Mermaid.
Reference layout
This skill keeps SKILL.md short. Reach into references/ and scripts/
when you need depth. All references are verified against the BESSER version shown in the README
badge; where behaviour changed after it, the reference says so.
What ships with it
14 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/agents.md 18 KB
- references/class-diagram.md 15 KB
- references/delivering-models.md 2.5 KB
- references/deployment.md 9.6 KB
- references/feature-models.md 6.9 KB
- references/gui-models.md 2.6 KB
- references/neural-networks.md 13 KB
- references/object-models.md 11 KB
- references/ocl.md 11 KB
- references/plantuml.md 2.2 KB
- references/project.md 4.5 KB
- references/quantum.md 8.1 KB
- references/state-machines.md 6.9 KB
- scripts/scaffold_model.py 4.0 KB runs code
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 Changed 1d1ef81ca954
- 12d ago First seen · 288 lines · 343 tokens per session scan A 90bec2fd6d93
besser-user is a skill published in the GitHub repository BESSER-PEARL/BESSER-Skills (8 stars, last pushed today), licensed Apache-2.0. It adds 343 tokens to every session and 3,237 once invoked, about $0.0017 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.
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.
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.