Borrowing it
Nothing to install: this file belongs to frostney/GocciaScript. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frostney/GocciaScript/main/.agents/skills/agent-writing/SKILL.mdgit clone --depth 1 https://github.com/frostney/GocciaScriptWrote 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/frostney/gocciascript/agent-writing)<a href="https://agentmods.dev/skills/frostney/gocciascript/agent-writing"><img src="https://agentmods.dev/badge/skills/frostney/gocciascript/agent-writing/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/frostney/gocciascript/agent-writing"><img src="https://agentmods.dev/badge/skills/frostney/gocciascript/agent-writing.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 | $0.00042 | $0.01975 |
| Opus 5.5 | $0.00017 | $0.00790 |
| Sonnet 5.5 | $0.00008 | $0.00395 |
| Haiku 4.5 | $0.00004 | $0.00198 |
Grade A, and why
agent-writing 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent writing
Write for the reader and the artifact. Lead with the answer, outcome, decision, or required action. Preserve every material fact, caveat, settled decision, and next action before removing lower-value detail.
Keep the boundary clear
This skill governs an agent's communication with people and the engineering artifacts the agent drafts for collaboration. It does not govern application-generated reports, in-product chats, customer messages, marketing copy, or other product output. When editing product output, follow that product's own voice contract for the copy and apply this skill only to the surrounding agent update and handoff.
Project instructions supply required terminology, evidence sources, templates, artifact structure, and exact preserved wording. They do not import a product voice into the agent's conversation. Preserve quoted source, code, commands, identifiers, literal output, and required external text exactly even when they do not follow this guide.
Match the response to its job
- A direct answer starts with the answer and adds only necessary qualification or evidence.
- A progress update starts with a result, blocker, decision, or correction. Add the next action only when it helps the reader.
- A final handoff states the outcome, exact validation, including any check that failed before it passed and what fixed it, material caveats or residual work, and exact artifact locations when artifacts exist.
- A review reply or retrospective impact item states the finding or impact and its consequence or resolution.
- A correction first re-runs the check behind the claim when it can. It states the corrected fact first, then the incorrect claim, the source or process failure, each affected conclusion, such as whether the branch is ready, and the prevention or next validation step. It does not lead with an apology.
- A durable artifact follows its project template and preserves the complete decision surface, evidence, and lifecycle state. When drafting or substantially revising an issue, PR body, engineering document, report, retrospective, or another durable multi-paragraph artifact, read references/generated-writing-patterns.md.
What ships with it
5 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.
- yesterday Changed · +13 lines 128ece1b8c5d
- 22d ago Changed · +3 lines c2f8ed4fd84d
- 26d ago Changed · +3 lines · +20 tokens per session f694404394eb
- 29d ago First seen · 158 lines · 22 tokens per session scan A a00f7a6a2c89
agent-writing is a skill published in the GitHub repository frostney/GocciaScript (20 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,975 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 2026-09-26.
Other skills, from other repositories
javascript-expert
Expert-level JavaScript development with modern ES2024+ features, Node.js, npm ecosystem, and best practices. Use when the user mentions ECMAScript, ES2024, Node.js, npm, or web, or when the task involves Modern JavaScript, Node.js Development, Modern Tooling, or Functional Programming.
qcad
Use when editing DXF files with a professional open-source 2D CAD application — CAM output, part libraries, isometric projection. QCAD: open-source 2D CAD with DXF as native format, scriptable via ECMAScript.
git-step-commit
Analyze Git changes, split them into coherent commits, infer message language and format, optionally close supplied GitHub issues, and execute safely. Manage persistent global or repository preferences for review versus direct submission and automatic or specified commit-message language through native Git config.…
manage-prd-docs
Automatically manage product requirements across current decisions in docs/PRD.md and docs/prd/, mature future plans under docs/plans/, and active implementation under docs/work/. Use whenever the conversation discusses, clarifies, versions, plans, implements, completes, splits, or migrates a product requirement or…
modernize-ecmascript
A guide for writing or reviewing JavaScript and TypeScript using newer ECMAScript language features. ECMAScript is the standard behind JavaScript, and the guide checks whether the project's tools and target browsers or runtimes can handle each feature.
file-line-audit
Audit oversized source files in a repository. Apply repository .gitignore rules plus extra exclude patterns, filter candidate files with include glob patterns, count physical lines, and output only files at or above the threshold. Use this skill when the user asks to find long files, review file-length distribution…