goal-creator

goal-creator is a skill for Claude Code, Codex from zebbern/pocmap. It costs 75 tokens per session (1,977 once invoked), scanned A, original, MIT.

A guide for writing reusable /goal directives: instructions that define an agent workflow’s desired result and how to check it.

In plain words
What is it for?
Use it to define outcomes, choose a workflow category, add constraints, describe independent checks, and audit a goal before using it.
Why use it?
It turns vague expectations into observable success criteria, limits, and verification steps that can be reused across runs.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/zebbern/pocmap/goal-creator
Any agent
npx skills add zebbern/pocmap --skill goal-creator
Clone the repo
git clone --depth 1 https://github.com/zebbern/pocmap

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-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/zebbern/pocmap/goal-creator.svg)](https://agentmods.dev/skills/zebbern/pocmap/goal-creator)
Your own site
<a href="https://agentmods.dev/skills/zebbern/pocmap/goal-creator"><img src="https://agentmods.dev/badge/skills/zebbern/pocmap/goal-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,977 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00075 $0.01977
Opus 5 $0.00037 $0.00988
Sonnet 5 $0.00015 $0.00395
Haiku 4.5 $0.00007 $0.00198

Measured 3d ago against content hash b6d3b3d49724, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goal-creator 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 3d 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-creator/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/goal Creator

Create reusable, testable, outcome-oriented success standards that guide agents across repeated runs. A /goal is not a one-off prompt - it is a durable operating instruction that defines what good execution looks like.

Core Workflow

Creating a /goal follows these steps:

  1. Define the outcome - what does success look like in observable terms?
  2. Select category - which workflow stage is this for? (see categories below)
  3. Apply a template - fill in the master template or select an alternate
  4. Add constraints - what must NOT happen? what boundaries apply?
  5. Define verification - how will an independent checker confirm success?
  6. Run quality audit - apply the pre-flight checklist before delivering

What a /goal Is

A /goal directive is a declarative, outcome-oriented specification of what success looks like - independent of execution path. It is:

  • Enduring - reusable across multiple sessions, not one-off
  • Evaluable - an independent checker can verify achievement
  • Decomposable - can be broken into sub-goals with dependencies
  • Role-anchored - tied to a specific agent responsibility

What a /goal Is Not

Format What It Specifies /goal Difference
One-off prompt A single task invocation Durable standard, not transient
System instruction How the agent should behave (identity, tone) What the agent must achieve (outcome)
Checklist Steps to execute Success conditions to meet
Acceptance criteria Verifiable conditions for one feature Reusable standard for a class of work
User story User need from product perspective Agent responsibility from execution perspective
SOP Procedural "how to" instructions Outcome specification - "what done means"

Rule of thumb: Use a /goal when you need a reusable success standard. Use other formats for one-time tasks, identity definition, procedure lists, or feature-level verification.

Read the full file on GitHub · 197 lines

Files

What ships with it

4 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.

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. 3d ago First seen · 197 lines · 75 tokens per session scan A b6d3b3d49724

Subscribe to this mod's changes

goal-creator is a skill published in the GitHub repository zebbern/pocmap (5 stars, last pushed 10d ago), licensed MIT. It adds 75 tokens to every session and 1,977 once invoked, about $0.0004 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

osv-ui

Security auditing skill for scanning CVE vulnerabilities across npm, Python, Go, and Rust projects using osv-ui. Opens a visual browser dashboard for human review, then applies fixes with explicit confirmation.

toan203/osv-ui · 42 tokens

write-cve-rule

Write, debug, or validate a CVEhound detection rule (.cocci or .grep) for a Linux kernel CVE. Use when adding a rule under cvehound/cve/, when a rule's slow tests fail, or when asked why a rule does or doesn't fire on a kernel tree. Not for general Coccinelle work outside this repository.

evdenis/cvehound · 78 tokens

code-audit-system

CVE-oriented multi-agent code audit system. Use when user provides a git repository URL for vulnerability discovery with the goal of submitting CVEs. This skill orchestrates subagents to find exploitable vulnerabilities (RCE, SQLi, Auth Bypass, etc.), write weaponized POCs, and generate CVE-ready reports. ALWAYS use…

UserB1ank/code-audit-system · 97 tokens

feature-spec

Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.

davepoon/buildwithclaude · 32 tokens

gmgn-wallet-score

Score any wallet address across three angles — profitability (a real track-record score: is this trader actually good?), copy-tradeability (can YOU actually capture what it makes, plus a latency/slippage/gas backtest), and Dev reputation (if it's mostly a token launcher, how trustworthy are its launches) — plus…

GMGNAI/gmgn-skills · 0 tokens

Security Audit Reporter

Triage raw security-scan findings (hardcoded secrets, injection patterns, vulnerable dependencies) into a prioritized, actionable security audit report. Use for security audit, code audit, vulnerability triage, and risk review.

AgentEra/Agently · 47 tokens