aget-go

aget-go is a skill for Claude Code from aget-framework/aget. It costs 48 tokens per session (2,271 once invoked), scanned A, original, Apache-2.0.

An authorization skill that records a clear, limited approval to begin specified work. It checks the approval against requirements, coherence, and available evidence, but does not perform the work itself.

In plain words
What is it for?
Use it to document who approved what, verify the three required principles, and release a separate execution step within that scope.
Why use it?
It makes the scope of a decision auditable instead of leaving approval as an unclear message in a conversation.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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/aget-framework/aget/aget-go
Any agent
npx skills add aget-framework/aget --skill aget-go
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-go

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/aget/aget-go.svg)](https://agentmods.dev/skills/aget-framework/aget/aget-go)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-go"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-go.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,271 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 5.1 $0.00048 $0.02271
Opus 5 $0.00024 $0.01136
Sonnet 5 $0.00010 $0.00454
Haiku 4.5 $0.00005 $0.00227

Measured 6d ago against content hash 35ad649893f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

aget-go 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 6d 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.

.claude/skills/aget-go/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aget-go

Record principal authorization to proceed with a scoped piece of work, with Healthy Friction enforcement of three principles before release-to-execute.

Purpose

Across the fleet, "GO" signals from the principal vary in clarity (yes, proceed, do it, ok), in scope (gate? action? entire goal? whole session?), and in audit value (none — they're free-text in the conversation). When the principal subsequently asks "what did we authorize?", the only record is the conversation log. This skill formalizes GO as an explicit, scoped, principle-checked, audit-traceable authorization act.

Healthy Friction posture (Tier 2 #11): friction MUST occur (mandatory verification of three principles); blocking is principal-elected (override preserved with reason). Distinct from Advisory (no friction) and Strict (hard block).

Composition discipline: this skill authorizes; it does NOT execute the authorized work. Execution is a separate act performed by the agent under the released authorization.

Evidence

L854 (Spec-First Applied Selectively — awareness alone is insufficient), L466 (Question Is Not Approval), L178 (Human Override Principle — acknowledge / commit / execute), L671 (Classification Without Consequence — anti-pattern Healthy Friction prevents), L42 (Stop At Gate Boundaries). Espanso compensating-control retirement: ;;g*pr* triggers retired in favor of governed ;;ago*. [instance-only per L600]

Input

$ARGUMENTS

Flag Default Purpose
--scope <gate|action|goal|session> resolve from context What is being authorized
--principles <triad> svc-ed (spec+verify, coherence, evidence-driven) Which principle pre-conditions to verify
--count N --shape {actions|goals} absent Compose with delegate skill (propose-actions / propose-goals)
--dry-run false Produce report without writing record
--record-only false Write record but do NOT signal release-to-execute
--reason <text> absent Required when overriding an UNMET pre-condition

Read the full file on GitHub · 161 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. 6d ago First seen · 161 lines · 48 tokens per session scan A 35ad649893f3

Subscribe to this mod's changes

aget-go is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,271 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.