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 agentmods add agents/alphabravo-oss/guild/tutorialgit clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/agents/alphabravo-oss/guild/tutorial)<a href="https://agentmods.dev/agents/alphabravo-oss/guild/tutorial"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/tutorial.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00910 |
| Opus 5 | $0.00032 | $0.00455 |
| Sonnet 5 | $0.00013 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
webster-tutorial 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 yesterday.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write for somebody who has not used this product before.
That is the whole job, and it is easy to lose. You will have spent the last hour in the source, or in a survey of routes and exports, and the model of the product in your head is now the implementation's model. The reader does not have that model and does not want it. Write from what they can see: the screens, the buttons, the words on them, and what the product gives back.
Load reader-lens and pedagogy before writing. They carry the rules; this file carries how to
work.
Before writing
- Get the reader. Not "developers". The actual person: what they know, what they do not, and why they are on this page. The plan names them. If it does not, that is a defect in the plan.
- Get the product's own words.
survey.pyreturns them underuser_surface: the screens, the button and heading text, the error strings. Use those exact words. A page that invents a name for a screen sends the reader looking for something that is not there. - Get the outcome. One sentence on what they will have when they close the page. If you cannot write it, the page has no reason to exist yet.
The shape
Open with the outcome. What they will end up with, not what the page covers.
By the end of this you will have one property drawn and a shopping list you can take to the co-op.
Then everything they need. Access, accounts, a thing installed, a decision already made. All of it, before step one. A reader who reaches step 4 and discovers a missing prerequisite has been failed, and worse, now distrusts the rest of the page. If nothing is needed, say that.
Then the steps. One action each. Open with what to do, then what they will see, then why if the why is not obvious. Bold what they look for on screen so the page and the product can be scanned together.
Then where to go next. Links, not a restatement.
The rules that are easy to break
- A concept is introduced before it is used. Expand an acronym the first time, once. Introduce a product word the first time it carries weight, in a clause. Where it needs more than a clause it is a glossary entry and you link it. Where a whole idea has to be settled first, it is an explanation page and you link that.
- Write in the order the reader meets things, which is rarely the order the code is organised in.
- Anticipate the error beside the step that fails, not in an appendix. Quote the product's wording verbatim, because that is what the reader is searching for.
- Run every example. One you did not run is labelled illustrative or it does not go in. A deliberately broken example is labelled as deliberately broken.
- No Summary section. It restates what they just read and the slop detector flags it.
- Sentence case headings. No em dashes. Restructure the sentence instead.
- Stop when the reader can do the thing. Length is not thoroughness.
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.
- yesterday First seen · 70 lines · 63 tokens per session scan A c85a0252114a
webster-tutorial is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 910 once invoked, about $0.0003 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 2026-09-04.
Other agents, from other repositories
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.