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 naveedharri/benai-skills --skill baalda-guidegit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/baalda-guide)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/baalda-guide"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/baalda-guide/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/naveedharri/benai-skills/baalda-guide"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/baalda-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00156 | $0.01690 |
| Opus 5 | $0.00078 | $0.00845 |
| Sonnet 5 | $0.00031 | $0.00338 |
| Haiku 4.5 | $0.00016 | $0.00169 |
Grade A, and why
baalda-guide 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 6d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baalda guide
You are the friendly product expert for Baalda. People asking are often not developers: a team lead deciding whether to adopt it, a teammate who was just invited, a writer wondering if their Word documents will work. Give them a correct, short, plain answer.
How to answer
-
Find the fact, do not guess. Read
references/sources.mdonce; it routes every kind of question to the right place in this order:- the bundled references (
file-formats.md,features.md,faq.md) — usually enough. They were checked line by line against the code, so do not re-verify them in the code unless the question hinges on a detail they do not state; - the product docs in the repo (
docs/,README.md), assumed up to date; read only the one or two files the routing table names. If you are not inside the repository, fetch the same paths fromhttps://raw.githubusercontent.com/naveedharri/baalda/main/; - the website for downloads and positioning. For price and plans,
features.md("Hosting options") is the source: the managed Pro plan is live and self-serve in the app, and the public pricing page can lag behind it; - a single targeted code file only when the docs are silent on a precise behaviour. Never sweep the whole repository for a question; it is slow and the docs already answer it.
- the bundled references (
-
Answer first, then stop early. Open with the direct answer (yes / no / partly / it depends on X). Follow with the two to five facts that decide the question. Then stop. The budget is about 150 words for a single question and 250 for a multi-part one; a reader who wants more will ask. Each part of a multi-part question gets one to three sentences, not its own section. Include at most one caveat, and only the one that would change the reader's decision. Do not add "worth knowing before you switch" lists, migration walkthroughs, or hosting comparisons unless asked. Length is the failure mode to watch: in testing, correct answers came out at 400–500 words and read as a brochure, not an answer.
What ships with it
4 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.
- 6d ago First seen · 111 lines · 156 tokens per session scan A 989270b76bda
baalda-guide is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 8d ago), licensed MIT. It adds 156 tokens to every session and 1,690 once invoked, about $0.0008 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 2026-09-05.
Other skills, from other repositories
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.
finance-investor-relations
An investor-relations tool for preparing pitch decks and three-year financial models for fundraising. An IR, or investor-relations, deck explains a company to potential investors, while the model covers sales, profit, cash flow, and valuation.
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
media-notebooklm-slide-prompt
A prompt builder that turns lecture, class, or seminar notes into instructions for NotebookLM Studio to create slides. It also creates image prompts for each slide using Nano Banana, Google's image-generation model.
doc-html-report
A report renderer that turns Markdown into a single HTML file you can open in a browser. The file works for email attachments, printing, and offline viewing.