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-workflowgit 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-workflow)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/writer-workflow"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/writer-workflow/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-workflow"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/writer-workflow.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 | $0.00039 | $0.00550 |
| Opus 5.5 | $0.00016 | $0.00220 |
| Sonnet 5.5 | $0.00008 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
writer-workflow 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing workflow
When to use
Use for multi-step fiction work, especially when continuing across sessions or choosing which writing specialty to apply.
Inputs and assumptions
Identify the project, current task, output format, language, audience, desired voice, and requested scope. Saved manuscript evidence takes precedence over an unsupported recollection from chat.
Portable workflow
- Read the project workflow and inspect the saved project state.
- Separate format, genre, style, and unit of work. Read format guidance and style choices only as needed.
- Choose relevant specialist skills. When the author asks to learn or the project uses beginner guidance, load beginner coaching and start with one small step. Do not apply it to every new project. Planning uses brainstorming and outlining. Drafting uses prose, the medium skill, and continuity. Revision uses critique and voice checks. Visual adaptation uses adaptation and manga guidance.
- Clarify only missing decisions that affect this deliverable. A new book starts with an agreed direction, not automatic whole-book generation. For a beginner, a rough scene idea is enough to begin practicing; a full outline is not a prerequisite.
- Complete one bounded step. Save authorized outputs, verify them, and record the next step. Stop at an author decision rather than guessing approval.
Safety and side effects
Creating and drafting can write local files. Reviewing is read-only. Preserve existing prose and keep proposed ideas separate from canon. Do not install, publish, upload, or generate images merely to run a writing workflow.
Scripts, references, and dependencies
No scripts or external services required. Specialist instructions live in sibling skill directories. The shared references define file responsibilities and medium-specific checks.
Verification
Confirm the requested scope was delivered, saved paths exist when saving was requested, the checkpoint matches the files, and unresolved choices remain visible. Do not report a reserved target as a finished chapter.
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 · 40 lines · 39 tokens per session scan A 611b88b4cca7
writer-workflow is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (91 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 550 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
delegation
Delegates independent work to worker agents through the Task tool, choosing between the explore scout and the ml, biology, physics, chemistry and data specialists, writing a self-contained brief for a worker that cannot see the conversation, setting boundaries on files and compute, using two independent annotators…
ui-control
Open a panel in agentglass's own window, read what is open, or read and change one of its settings. Use when the person asks you to "show me" a Settings page, the machine panel, the bench, a Git modal or a file in agentglass; when you need to know what they are looking at, what is in a chat or on the bench, or what a…
a0-development
Develop or operate Agent Zero: projects, chats, tasks, framework, tools and API/WebUI.
google-calendar
Google Calendar via gws: list events, create, accept, find free time.
google-drive
Google Drive via gws: search, list, upload, download, share.
google-forms
Google Forms via gws: create forms, add items, read responses.