goalx

goalx is a skill for Claude Code, Codex from vonbai/goalx. It costs 33 tokens per session (1,486 once invoked), scanned A, original, MIT.

A system for managing long-running autonomous work in a software project, including saved progress, investigation, implementation, recovery, and continued improvement.

In plain words
What is it for?
Use it to run a project investigation, implement a change, audit a codebase, recover a stopped run, or continue an earlier task.
Why use it?
It keeps work organised across multiple runs instead of treating every request as a one-off task. Goals describe the desired end result so progress can continue after interruptions.

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/vonbai/goalx/skill
Any agent
npx skills add vonbai/goalx --skill skill
Clone the repo
git clone --depth 1 https://github.com/vonbai/goalx

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 goalx

README.md
[![agentmods](https://agentmods.dev/badge/skills/vonbai/goalx/skill.svg)](https://agentmods.dev/skills/vonbai/goalx/skill)
Your own site
<a href="https://agentmods.dev/skills/vonbai/goalx/skill"><img src="https://agentmods.dev/badge/skills/vonbai/goalx/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,486 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 $0.00033 $0.01486
Opus 5 $0.00016 $0.00743
Sonnet 5 $0.00007 $0.00297
Haiku 4.5 $0.00003 $0.00149

Measured 4d ago against content hash 8c08b1caed14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goalx 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.

skill/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GoalX

GoalX is the default operating system for durable autonomous work in this project. Use it when the user wants a real run with durable state, not a one-shot answer.

Use GoalX By Default

Prefer GoalX when the user wants:

  • autonomous investigation
  • autonomous implementation
  • a repo audit with follow-through
  • durable observation and redirection
  • a stopped or stranded run recovered in place
  • a saved run continued into the next phase
  • continuous improvement over time

Do not default to manual tmux orchestration. Use GoalX commands and durable surfaces.

Write Better Goals

Write the desired end state, not a checklist.

Good:

goalx run "users can complete the core workflow reliably in production"
goalx run "the codebase has a high-quality architecture audit and a prioritized fix plan"
goalx run "this project keeps getting better until the budget runs out" --intent evolve --budget 8h

Bad:

goalx run "1. inspect auth 2. patch middleware 3. update tests"

When the user is vague, keep it outcome-focused:

  • "make deploy work" -> goalx run "the project deploys cleanly to the target host in one step"
  • "audit this repo" -> goalx run "full audit of this project with an actionable improvement plan"

Default Operator Loop

Use this by default:

goalx run "goal"
goalx run --objective "goal"
goalx run --objective-file /abs/path/to/objective.txt
goalx status
goalx observe
goalx context
goalx afford
goalx tell "redirect"
goalx verify
goalx result
goalx save

Quick meanings:

  • status: compact durable control summary
  • observe: full diagnostic path for live transport and runtime facts
  • context: canonical identity, paths, cognition, and assurance facts
  • afford: current run-scoped command surface
  • tell: durable redirect to master or a worker
  • verify: record assurance evidence, not completion
  • save: export a saved run for continuation

Use goalx schema <surface> before goalx durable write <surface> ... when authoring machine-consumed state.

Read the full file on GitHub · 213 lines

Files

What ships with it

2 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. 4d ago First seen · 213 lines · 33 tokens per session scan A 8c08b1caed14

Subscribe to this mod's changes

goalx is a skill published in the GitHub repository vonbai/goalx (59 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 1,486 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

timeline-creator

Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.

mhattingpete/claude-skills-marketplace · 47 tokens

bootstrap-prd

Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.

joshukraine/dotfiles · 25 tokens

glab-issue

Create, view, update, and manage GitLab issues. Use when working with issue tracking, bug reports, feature requests, or task management. Operations include creating issues, listing with filters, viewing details, adding comments/notes, updating labels/assignees/milestones, closing/reopening, and board management.…

vince-winkintel/gitlab-cli-skills · 89 tokens

sales-ops

Set up and run Airtable-based sales operations and CRM workflows — pipeline management, account and renewal management, deal desk, RFP / tender pipelines, partner CRMs, sales forecasting, vertical CRMs (real estate, mortgage, brokerage, capital markets, public works, nonprofit), and AI-native lean stacks…

Airtable/skills · 164 tokens

jira

Search and manage Jira issues using JQL queries, create/update tickets, and manage workflows. Use when asked to find Jira tickets, check the backlog, manage sprints, track bugs, or work with Atlassian project management.

odyssey4me/agent-skills · 48 tokens

github

Use this skill when Enoch needs to coordinate work with GitHub: branches, pull requests, issues, reviews, comments, checks, and merges.

our-ark/enoch · 0 tokens