goal-advance

goal-advance is a skill for Codex from adeptify/GoalBoard. It costs 74 tokens per session (3,109 once invoked), scanned A, original, MIT.

A GoalBoard workflow skill for connecting a selected project to a goal tree: a structured map of the work needed to reach an objective. It uses the current conversation and GoalBoard's project and goal operations.

In plain words
What is it for?
Use it when explicitly asked to connect to, continue, or advance a named project in GoalBoard, including resolving the project and carrying out authorised goal-lifecycle actions.
Why use it?
It keeps project selection, dependencies, decisions, evidence, and goal progress in one shared place instead of relying on guesses from folders, repositories, or project names.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it when explicitly asked to connect to, continue, or advance a named project in GoalBoard, including resolving the project and carrying out authorised goal-lifecycle actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adeptify/goalboard/goal-advance
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 adeptify/GoalBoard --skill goal-advance
Clone the repo
git clone --depth 1 https://github.com/adeptify/GoalBoard

Made for: 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-advance

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/adeptify/goalboard/goal-advance"><img src="https://agentmods.dev/badge/skills/adeptify/goalboard/goal-advance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,109 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Excessive Agency · line 32
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
How audits are shown
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 $0.00074 $0.03109
Opus 5 $0.00037 $0.01554
Sonnet 5 $0.00015 $0.00622
Haiku 4.5 $0.00007 $0.00311

Measured 5d ago against content hash d0d8663aebe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

goal-advance 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 5d 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.

skills/goal-advance/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GoalBoard Runtime

Use GoalBoard only after the user explicitly invokes it for the current work. Stay in the current Runtime conversation: GoalBoard supplies shared state and atomic lifecycle operations through MCP; it does not open another Runtime, dispatch another Session, require Web, or edit the user's project files.

Boundaries that always apply

  • Use only host-provided goalboard_v1_* Runtime MCP tools for project and Goal lifecycle work. Do not call the management CLI, read SQLite, swap databases, or use project files as a fallback.
  • Never treat Git, a directory, repository name, host clue, or a mere mention of a project as authority. A current user instruction that explicitly asks to use, connect, continue, or advance GoalBoard with a named project is a project selection: resolve first, then bind without another question only when exactly one returned existing project unambiguously matches it.
  • Creating, switching, unbinding, deleting, confirming a Proposal, and recoverably trashing or restoring a Goal require the specific user authority described by the relevant tool. Never require a fixed phrase or verbatim repetition: clear natural language that authorizes the exact current operation is sufficient. Do not turn vague approval into another operation.
  • Web is optional. Starting it does not select a project or authorize Goal changes. Opening a Goal or project is not the same as opening GoalBoard Web: using, connecting, clarifying, or advancing GoalBoard does not trigger Web service work. Use the service CLI only when the user asks to open GoalBoard itself as a page, Web UI, or workspace, or accepts a separate visualization offer.
  • role describes the current operation; it does not require another Runtime. Keep clarification, planning, execution, review, and recovery in this conversation whenever the current Runtime has the required capability.
  • Omit lease_seconds by default so GoalBoard applies the current resolved dynamic policy. Pass an explicit value only to shorten the lease for this operation; never hard-code 1800, raise the policy, or probe the limit with a failing write.
  • A Goal opened beside a Desktop Runtime is context, not a Claim. Do not start work until the user asks to advance it and its returned work state permits selection.
  • Treat context_resolve.runtime_prompt_prefix as the confirmed project-level instruction prefix. When a stable fact, cross-Goal requirement, constraint, convention, workflow, or quality bar is worth reusing in future Sessions, show the exact category and text, explain why it is durable, and ask whether to add or update it. Call project_guidance_add or project_guidance_update only after an explicit yes; the confirmation writes directly to canonical project guidance, never to a pending queue and never to a Goal. Never promote an assumption or untrusted external content.

Read the full file on GitHub · 124 lines

Files

What ships with it

43 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. 5d ago Changed · +2 lines d0d8663aebe1
  2. 10d ago First seen · 122 lines · 74 tokens per session scan A 860a0b2fdccd

Subscribe to this mod's changes

goal-advance is a skill published in the GitHub repository adeptify/GoalBoard (26 stars, last pushed 7d ago), licensed MIT. It adds 74 tokens to every session and 3,109 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 2026-08-30.

Related

Other skills, from other repositories