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 vonbai/goalx --skill skillgit clone --depth 1 https://github.com/vonbai/goalxWrote 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/vonbai/goalx/skill)<a href="https://agentmods.dev/skills/vonbai/goalx/skill"><img src="https://agentmods.dev/badge/skills/vonbai/goalx/skill/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/vonbai/goalx/skill"><img src="https://agentmods.dev/badge/skills/vonbai/goalx/skill.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 | $0.00033 | $0.01486 |
| Opus 5.5 | $0.00013 | $0.00594 |
| Sonnet 5.5 | $0.00007 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00149 |
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 1mo 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 — 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 summaryobserve: full diagnostic path for live transport and runtime factscontext: canonical identity, paths, cognition, and assurance factsafford: current run-scoped command surfacetell: durable redirect to master or a workerverify: record assurance evidence, not completionsave: export a saved run for continuation
Use goalx schema <surface> before goalx durable write <surface> ... when authoring machine-consumed state.
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.
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.
- 1mo ago First seen · 213 lines · 33 tokens per session scan A 8c08b1caed14
goalx is a skill published in the GitHub repository vonbai/goalx (59 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 1,486 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…