aget: Skill for Claude Code

.claude/skills/aget-propose-goals/SKILL.md

aget-propose-goals is a skill for Claude Code from aget-framework/aget. It costs 45 tokens per session (3,683 once invoked), scanned A, original, Apache-2.0.

A skill for proposing several possible goals for the current work session, ranking them with a defined scoring rubric, and recording the results for later review.

In plain words
What is it for?
Use it when deciding what to pursue next, comparing candidate session goals, presenting a ranked choice, and creating an auditable record of that decision.
Why use it?
It makes pivot decisions explicit and preserves why one goal was selected instead of relying on an informal conversation.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event.

This is aget-framework/aget's own configuration. It tells Claude Code how to work on aget itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aget configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/record_goals_ext.py --record --session <current session file> \.

Reuse

Borrowing it

Nothing to install: this file belongs to aget-framework/aget. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aget-framework/aget/main/.claude/skills/aget-propose-goals/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aget-framework/aget

Made for: Claude Code.

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 aget-propose-goals

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/aget/aget-propose-goals/github.svg)](https://agentmods.dev/skills/aget-framework/aget/aget-propose-goals)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-propose-goals"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-propose-goals/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 aget-propose-goals

Your own site · 80×15
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-propose-goals"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-propose-goals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,683 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
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 $0.00045 $0.03683
Opus 5 $0.00023 $0.01842
Sonnet 5 $0.00009 $0.00737
Haiku 4.5 $0.00005 $0.00368

Measured 9d ago against content hash 980680d470a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aget-propose-goals 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/aget-propose-goals/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aget-propose-goals

Propose N ranked candidate session-goals scored ex-ante by RUBRIC_goal_selection_v1.0, recorded for retrospective audit. The goal-altitude sibling of /aget-propose-actions (action-altitude).

Purpose

Formalize the mid-session candidate-goals pattern. When a session faces a pivot decision — the principal asks "what should we do next?" or the agent independently identifies a choice point — the prior ad-hoc pattern produced N candidate goals in conversation, informally described, with no durable scored artifact. This skill:

  • Generates N candidate goals in divergent-proposal mode (L677), each with a one-sentence thrust + beneficiary tag
  • Scores each ex-ante with RUBRIC_goal_selection_v1.0 (5 dimensions, /15)
  • Presents ranked by total score with the dominant dimension surfaced per candidate
  • Records the scored candidate set in the session file so retrospectives can audit "why did we pivot to G2?"

Plurality (L1067): propose-goals is PLURAL — a candidate-set generator (output is selected, not scaffolded), structurally a sibling of propose-actions, NOT of the singular commitment-pipeline skills (propose-project/propose-skill). It has no create counterpart; a selected goal funnels into the (separate, downstream) create-goal committer when the Goal-tier lands.

Evidence: SP-017 (planning/skill-proposals/PROPOSAL_aget-propose-goals.md); parent L845 (session-pivot rubric gap); L1067 (two-propose semantics); RUBRIC_goal_selection_v1.0 (the scoring engine, reflexively validated G3>G1>G2).

Input

<topic> — optional focus for the candidate goals.

Parameters (parsed from natural language or flags):

Parameter Source Default Grammar
count First number in prompt 3 (goal-altitude default; heavier than the 5-action default per L693) "propose N candidate goals"
focus Remainder of prompt Session mandate "focus on X" / "for Y"
budget Context % or time hint Remaining session capacity "within remaining context"

Read the full file on GitHub · 212 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. 9d ago First seen · 212 lines · 45 tokens per session scan A 980680d470a2

Subscribe to this mod's changes

aget-propose-goals is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 3,683 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.