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 Firstp1ck/pi-coding-agent-forge --skill writer-beginnergit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forgeWrote 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/firstp1ck/pi-coding-agent-forge/writer-beginner)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/writer-beginner"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/writer-beginner/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/firstp1ck/pi-coding-agent-forge/writer-beginner"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/writer-beginner.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 | $0.00053 | $0.00785 |
| Opus 5.5 | $0.00021 | $0.00314 |
| Sonnet 5.5 | $0.00011 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
writer-beginner 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 28d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Begin writing a story
When to use
Use when the author asks how to begin, says they lack writing experience, wants a concept explained, or chooses guided learning. Do not assume that every new project belongs to a beginner.
Inputs and assumptions
A feeling, character, place, what-if, or even "I don't know yet" is enough. A working title is a folder label, not a creative commitment. Use the author's language. Read any existing draft and learning notes before choosing a next step.
Portable workflow
- Read the beginner guide, then choose only the step relevant now. Never recite the entire guide as a course syllabus.
- Build on what the author has already shared. If they have no idea, offer a few distinct, concrete seeds or ask what sort of story they enjoy. Ask at most one question per reply and wait.
- Find a person who wants something and one thing making it difficult. Explain a writing term only when it helps with the next choice, using a short example from this story.
- Work toward one small scene. A few bullets about what happens next are enough preparation. Do not demand a full outline, ending, magic system, or detailed character biography.
- Let the author choose to try writing, write together, or see a short original example. Use an already stated preference instead of asking again. Never complete their exercise unless they ask; explicit requests for a drafted chapter still authorize drafting.
- Give feedback on one specific strength and one useful next improvement. Show a small before/after example when helpful, preserving their voice and story choices. Do not bury the author in corrections or empty praise.
- Save the current question or exercise, what the author actually tried, helpful feedback, and one next small step. Resume that work next time instead of restarting the introduction.
- Expand toward a chapter and a loose book plan when the author is ready. Skip familiar concepts and allow the author to leave guided learning at any time.
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.
- 28d ago First seen · 47 lines · 53 tokens per session scan A 50c1b22426d4
writer-beginner is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (91 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 785 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
opengeni-help
Answer questions about Opengeni setup, product integration, SDK/API behavior, billing, GitHub access, and development setup. Read the official product docs before making product-specific claims or replacing an application's AI provider. No installation is needed for this bundled guide.
omd-video
A pipeline that turns instructional videos into structured notes using both their visuals and audio. It is intended for videos such as lectures, tutorials, and courses where slides, diagrams, prompts, or code appear on screen.
teach
Teach the user a new skill or concept, within this workspace.
scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
notebooklm
Interact with Google NotebookLM (notebook.google.com) notebooks — chat with the AI, generate artifacts (slides, audio, video, mind maps, quizzes, flashcards, infographics, reports, data tables), manage sources (add URLs, YouTube, files, text), run research (fast/deep web research), and manage notes. Use whenever the…
mandu-explain
A reference guide to core Mandu concepts, including server-rendered pages, interactive islands, API handlers, access guards, shared API schemas, and server-side data loaders. Server-side rendering creates page HTML on the server before sending it to the browser.