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 liza-mas/liza --skill goal-writinggit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/liza-mas/liza/goal-writing)<a href="https://agentmods.dev/skills/liza-mas/liza/goal-writing"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/goal-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/liza-mas/liza/goal-writing"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/goal-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 | $0.00100 | $0.04371 |
| Opus 5 | $0.00050 | $0.02185 |
| Sonnet 5 | $0.00020 | $0.00874 |
| Haiku 4.5 | $0.00010 | $0.00437 |
Grade A, and why
goal-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 4d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Writing
Facilitate production of the document §BRAND_BINARY_NAME§ init --spec consumes. The human decides; you elicit, challenge, record, and verify.
Do not draft on invocation. Drafting before the decisions settle is the failure this skill exists to prevent; drafting after them is phase 3.
The rule this enforces
Agents may make implementation choices but not product decisions.
A run's quality ceiling is set by the decisions made before it starts. Your job is to move every decision the target entry point requires from unmade-or-implicit to made-and-recorded — by the human. Everything below derives from that one rule; nothing sits beside it.
A decision you made is not a decision the human made. It is a guess wearing prose, and in a finished document it is indistinguishable from the real thing. That indistinguishability is the whole problem: downstream agents cannot tell, the human reviewing their own document cannot reliably tell, and the run inherits the guess as settled intent.
Solid and lean
The rule says which decisions must be made. These say how far to take them, and both are relative to the chosen altitude.
Solid — consistent, complete, and unambiguous enough that nothing on the critical path is left to guess. "Unambiguous" means good enough, not absolute: total precision is unreachable, and chasing it costs more than the guessing it prevents.
Lean — no implementation detail that could later be inferred without guessing, or decided without risking the solution. Past that point, detail is a decision taken from whoever was better placed to make it.
The two bound each other. Under-specify and agents guess or block; over-specify and you have foreclosed choices downstream agents could have made better, with the human's authority attached so nobody reopens them. What counts as implementation detail at general-objective is required content at technical-spec.
Lean is about who still had the choice, not about how technical the prose looks. Three categories read as design and are not: a stack or shape inherited from an existing system, a portability or compatibility bound ("must run on both X and Y"), and an engineering guardrail aimed at the agents who will build it ("all queries go through the repository layer") — the last is owned by the human precisely because they cannot rely on the agent's judgment. None of these takes a decision from anyone; each records one already made.
What ships with it
1 file 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.
- 4d ago First seen · 196 lines · 100 tokens per session scan A 0ee51ab5be57
goal-writing is a skill published in the GitHub repository liza-mas/liza (387 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 4,371 once invoked, about $0.0005 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 2026-09-07.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…