goal-setting

goal-setting is a skill for Claude Code, Codex from wild-mental/goal-setting-skill. It costs 143 tokens per session (7,710 once invoked), scanned A, original, MIT.

A guide for creating structured /goal prompts for Claude Code. It organises a coding task into its scope, rules, completion checks, and constraints.

In plain words
What is it for?
Use it to write paste-ready /goal prompts for Claude Code, define the files and commands in scope, and specify measurable completion conditions.
Why use it?
It turns a vague request into a bounded task with observable checks, so the coding agent knows when to stop and how to verify its work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

Good fit Use it to write paste-ready /goal prompts for Claude Code, define the files and commands in scope, and specify measurable completion conditions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wild-mental/goal-setting-skill/goal-setting
Install

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.

Any agent
npx skills add wild-mental/goal-setting-skill --skill goal-setting
Clone the repo
git clone --depth 1 https://github.com/wild-mental/goal-setting-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for goal-setting

README.md
[![agentmods](https://agentmods.dev/badge/skills/wild-mental/goal-setting-skill/goal-setting/github.svg)](https://agentmods.dev/skills/wild-mental/goal-setting-skill/goal-setting)
Your own site
<a href="https://agentmods.dev/skills/wild-mental/goal-setting-skill/goal-setting"><img src="https://agentmods.dev/badge/skills/wild-mental/goal-setting-skill/goal-setting/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.

agentmods 80×15 button for goal-setting

Your own site · 80×15
<a href="https://agentmods.dev/skills/wild-mental/goal-setting-skill/goal-setting"><img src="https://agentmods.dev/badge/skills/wild-mental/goal-setting-skill/goal-setting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00143 $0.07710
Opus 5 $0.00072 $0.03855
Sonnet 5 $0.00029 $0.01542
Haiku 4.5 $0.00014 $0.00771

Measured 8d ago against content hash ef96149f5b95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

goal-setting 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 8d 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.

.agents/skills/goal-setting/SKILL.md · 522 lines

How it starts

The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal Setting Operating Rules

역할

이 스킬은 /goal실행하지 않는다. 사용자가 Claude Code의 /goal 명령에 그대로 붙여넣을 수 있는 구조화된 마크다운 프롬프트(Required 4섹션 + 필요 시 추가 섹션)를 함께 설계한다.

사용자의 모호한 요구 → [goal-setting] → 4섹션 구조의 /goal 프롬프트(필요 시 추가 섹션 포함)

산출물은 단일 마크다운 코드블록이며, 구조는 아래 Standard Template을 따른다. 추가 섹션(5)~)은 사용자 요청에 따라 유연하게 편성한다.

시작 시 확인

작업 시작 시 다음을 짧게 확인한다:

  1. 사용자가 어떤 작업을 /goal로 자동화하려 하는지 의도 한 줄
  2. 작업이 수행될 코드베이스/디렉터리 범위
  3. 사용 가능한 검증 명령(테스트·린트·타입체크·grep 등)이 프로젝트에 존재하는지

확인은 1턴에 묶어 처리한다. 답이 다 모이기 전에는 /goal 프롬프트를 출력하지 않는다.


기본 원칙

  1. 모든 /goal 프롬프트는 Required 4 Sections(목표·범위 / 세부규칙 / 종료조건+방법 / 제약)을 모두 갖춰야 한다.
  2. 모든 /goal 프롬프트는 Three Pillars 검증을 통과해야 한다.
  3. 평가자는 도구를 실행하지 않고 파일도 직접 읽지 않는다 — 증거는 대화에 드러나야 한다.
  4. 종료 조건 절(예: or stop after N turns, budget cap, queue empty)이 없으면 출력하지 않는다.
  5. 측정 불가 형용사(better, cleaner, perfect, fully)는 명령 기반 조건으로 환원한다.
  6. /goal 프롬프트는 단일 atomic 목표여야 한다 — 복합 목표는 분리된 /goal로 나눈다.
  7. 검증 명령은 사용자 프로젝트에 실제 존재하는 것만 사용한다.
  8. 출력은 시각적 행 구분자(---)로 4개 영역을 분리한다 — 상세 형식은 아래 Step 5 — Output을 단일 기준으로 따른다.
  9. 사용자가 이미 구조화된 장문 요구사항 프롬프트를 제시하면 템플릿에 끼워 맞추지 말고 원 구조를 보존해 <docs>/goals/original-requirements/에 저장한 뒤 ## 2) 작업 세부 규칙에서 그 파일을 참조한다 — 아래 산출물 외부화 규칙 A를 따른다.
  10. 생성된 /goal 본문이 4,000자를 초과하면 <docs>/goals/에 저장하고 대화에는 파일 호출 프롬프트만 제공한다 — 아래 산출물 외부화 규칙 B를 따른다.

Three Pillars (필수 통과 기준)

모든 /goal 프롬프트는 아래 세 기둥을 동시에 만족해야 한다.

1. Feasibility — 측정 가능한가?

완료 상태가 boolean(yes/no)으로 환원되는가?

표현 판정 환원 방향
make the app perfect ❌ Infeasible 정의 불가, 거부
improve the payment module ❌ Infeasible "어떤 명령이 통과하면 개선된 것인가?"로 환원
all tests in test/auth pass ✅ Feasible exit code로 판정
each file under 300 lines in src/payment/parts ✅ Feasible wc -l로 판정

2. Demonstrability — 대화로 증명 가능한가?

평가자는 transcript에 surface된 내용만 본다. 다음을 항상 확인:

  • Claude가 명령을 실제로 실행하고 출력을 대화에 남길 수 있는가?
  • 그 출력만 보고 evaluator가 yes라고 말할 수 있는가?
표현 판정 환원 방향
all files are correct ❌ Non-demonstrable 평가자가 파일을 못 봄
the bug is fixed ❌ Non-demonstrable "고쳤다"를 명령 출력으로 환원
npm test exits 0 and the result is shown in the conversation ✅ Demonstrable exit code가 대화에 남음
grep -rn legacyAuth src/ returns 0 matches in the conversation ✅ Demonstrable grep 결과가 대화에 남음

Read the full file on GitHub · 522 lines

Changes

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.

  1. 8d ago First seen · 522 lines · 143 tokens per session scan A ef96149f5b95

Subscribe to this mod's changes

goal-setting is a skill published in the GitHub repository wild-mental/goal-setting-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 143 tokens to every session and 7,710 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens