aget: Skill for Claude Code

.claude/skills/aget-create-goal/SKILL.md

aget-create-goal is a skill for Claude Code from aget-framework/aget. It costs 123 tokens per session (1,272 once invoked), scanned A, original, Apache-2.0.

A governed goal-creation workflow that records a chosen goal for future work, either in a project goals file or internal storage.

In plain words
What is it for?
Use it to commit a proposed goal as a durable project goal or mark it as aspirational for later consideration.
Why use it?
It prevents committed goals from being added informally and preserves their origin and status.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

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 →

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-create-goal/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-create-goal

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/aget/aget-create-goal.svg)](https://agentmods.dev/skills/aget-framework/aget/aget-create-goal)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-create-goal"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-create-goal.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,272 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.
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 $0.00123 $0.01272
Opus 5 $0.00062 $0.00636
Sonnet 5 $0.00025 $0.00254
Haiku 4.5 $0.00012 $0.00127

Measured 7d ago against content hash 20fb0a395297, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aget-create-goal 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 7d 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-create-goal/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aget-create-goal

Commit a Goal — a durable, named, cross-session outcome (C926) — into governed storage. The singular committer that consumes a /aget-propose-goals candidate; the create-side of the verb pair (L1067 two-propose semantics; L1085 plural-leads-singular).

Enforcement: D71-Strict (CAP-GOAL-008). Once invoked, direct Write/Edit of a committed-Goal section in governance/GOALS.md is PROHIBITED — creation MUST route through this skill, which writes the provenance field that the bypass check reads. Mirrors /aget-create-project and /aget-create-initiative.

Input

<candidate> — a selected /aget-propose-goals candidate, or a goal description. Flags: --aspirational (record to the agent-internal tier instead of committing).

Engine

The falsifiable core is scripts/create_goal.py (11 firing falsifiers in tests/test_create_goal.py, ADR-007). This skill orchestrates it; the script enforces the spec.

Steps

Step 0: Tier decision (REQ-3 two-tier)

  • Committed (default): a goal the principal commits to → structured section in governance/GOALS.md (principal-facing surface), D71-Strict.
  • Aspirational (--aspirational): a candidate not yet committed → .aget/goals/aspirational.jsonl (agent-internal), Advisory. Promotion aspirational→committed is a later create-goal (committed) act.

Step 1: Conflation guard (CAP-GOAL-002 / C930)

Reject a "goal" defined by workstreams/tasks rather than a measurable end-state. validate_outcome() fires on stream-enumeration with no outcome. If rejected, return the candidate to /aget-propose-project (it is a project, not a goal).

Step 2: Required fields

  • type ∈ {Achieve, Maintain, Soft} (CAP-GOAL-003)
  • ≥1 loop ⟨owner, trigger, review-action, consequence, cadence⟩ at creation (CAP-GOAL-004 / MP#12) — a Goal without a loop is an orphan that decays. The skill REFUSES to commit a loop-less Goal.
  • parent (Theme/Initiative) where one exists (CAP-GOAL-001)
  • status: active set at creation (CAP-GOAL-011)

Read the full file on GitHub · 66 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. 7d ago First seen · 66 lines · 123 tokens per session scan A 20fb0a395297

Subscribe to this mod's changes

aget-create-goal is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 123 tokens to every session and 1,272 once invoked, about $0.0006 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.