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 JuliaBesties/BestieTemplate.jl --skill bestie-featuresgit clone --depth 1 https://github.com/JuliaBesties/BestieTemplate.jlWrote 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/juliabesties/bestietemplate.jl/bestie-features)<a href="https://agentmods.dev/skills/juliabesties/bestietemplate.jl/bestie-features"><img src="https://agentmods.dev/badge/skills/juliabesties/bestietemplate.jl/bestie-features/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/juliabesties/bestietemplate.jl/bestie-features"><img src="https://agentmods.dev/badge/skills/juliabesties/bestietemplate.jl/bestie-features.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 29 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium MCP Rug Pull · line 13 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00071 | $0.02360 |
| Opus 5 | $0.00036 | $0.01180 |
| Sonnet 5 | $0.00014 | $0.00472 |
| Haiku 4.5 | $0.00007 | $0.00236 |
Grade A, and why
bestie-features 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 13d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding Bestie features to a package
bestie add-feature applies a named slice of the BestieTemplate copier template to an existing package: only the feature's files are written, everything else is left untouched. Requires only uv on the PATH.
bestie in the commands below stands for this full invocation:
uvx --from bestie-template bestie
(The --from is needed because the package is bestie-template and its command is bestie.)
Inline the full invocation in every command — do not rely on a shell alias or variable, which won't survive when each command runs in a fresh shell.
Workflow
-
Discover what can be added:
bestie list-features --jsonEach entry has
name,description,required_fields(answers you must be able to supply),requires_answers(needs an existing.copier-answers.yml), and optionallyoptional_files(extra config files written only if missing, keyed by the boolean answer that enables them). Feature names are exact (e.g. the testitem runner istestitem_cli, nottestitem); if you pass a name that doesn't exist, the error lists every valid name. -
Check the working tree before applying. A feature overwrites its
included_fileswithout warning, no conflict prompt and no backup —testitem_clireplaces an existingtest/runtests.jloutright, discarding whatever was there.optional_filesare the opposite: written only if missing, so an existing one (e.g. a hand-tuned.lychee.toml) is left untouched. Git is the only recovery path forincluded_files, so rungit statusfirst:- Uncommitted changes to any of the feature's
included_files: stop and tell the user those changes will be lost. Let them commit or stash before you continue. - A file the feature owns exists and is committed: say so and what will replace it, and get the user's go-ahead before applying.
- Not a git repository: do not apply. There is no way to undo it.
- Uncommitted changes to any of the feature's
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.
- 13d ago First seen · 91 lines · 71 tokens per session scan A 00ee188b3b11
bestie-features is a skill published in the GitHub repository JuliaBesties/BestieTemplate.jl (128 stars, last pushed 29d ago), licensed MPL-2.0. It adds 71 tokens to every session and 2,360 once invoked, about $0.0004 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
rust-skills
Comprehensive Rust coding guidelines with 265 rules across 26 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, concurrency, unsafe code, API design, memory optimization, performance, numeric safety, conversions, serde, pattern matching, macros…
karpathy-coding-principles
Use when andrej Karpathy's 4 coding principles — think before coding, simplicity first, surgical changes, goal-driven execution. Use when coding, reviewing code quality, reducing overengineering,.
rust-skills
Rust best practices — 179 rules across 14 categories for idiomatic, optimized Rust code.
observability
This skill should be used when the user asks about "observability", "logging", "metrics", "tracing", "monitoring", "structured logging", "log format", "log levels", "distributed tracing", "OpenTelemetry", "health checks", or needs guidance on implementing observability and monitoring requirements.
ai
This skill should be used when the user asks about "AI development", "AI coding", "AI assistant", "CLAUDE.md", "AI context", "AI guidelines", "code generation", "AI workflow", "AI review", "AI configuration", or needs guidance on configuring AI assistants and AI-assisted development workflows.
docs
This skill should be used when the user asks about "documentation", "README", "CHANGELOG", "CONTRIBUTING", "ADR", "architecture decision record", "changelog format", "keep a changelog", "doc comments", "API documentation", or needs guidance on project documentation requirements.