aget: Skill for Claude Code

.claude/skills/aget-enhance-spec/SKILL.md

aget-enhance-spec is a skill for Claude Code from aget-framework/aget. It costs 39 tokens per session (4,133 once invoked), scanned A, original, Apache-2.0.

A governed seven-phase workflow for creating or changing AGET specifications. Specifications are written rules that define how a system or process should work.

In plain words
What is it for?
Use it to create, update, add requirements to, connect, consolidate, or deprecate a specification.
Why use it?
It replaces ad-hoc specification edits with a repeatable process that includes validation and cross-referencing. Different change types can require different phases.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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 test -f .aget/patterns/sync/validate_spec_compliance.py && python3 .aget/patterns/sync/validate_spec_compliance.py <spec_path> 2>/dev/null || echo "Spec complia.

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-enhance-spec/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-enhance-spec

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-enhance-spec"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-enhance-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,133 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 $0.00039 $0.04133
Opus 5 $0.00019 $0.02067
Sonnet 5 $0.00008 $0.00827
Haiku 4.5 $0.00004 $0.00413

Measured 9d ago against content hash ba90b6098169, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aget-enhance-spec 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-enhance-spec/SKILL.md · 434 lines

How it starts

The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aget-enhance-spec

Guide agents through the core specification enhancement lifecycle. Provides governed workflow for spec creation, updates, cross-reference wiring, and validation.

Purpose

Replace ad-hoc specification enhancement with a repeatable, governed 7-phase process derived from 5 independent plans across 3 agents (L622). This is the Generator layer (ADR-008 step 3), built on SOP_specification_enhancement.md (Advisory) and SKILL-041 spec (Strict).

Input

$ARGUMENTS - Enhancement category and optional spec path.

Format: <CATEGORY> [spec-path] [--version <target-version>]

Categories: NEW, UPDATE, ADD-REQ, WIRE, CONSOLIDATE, DEPRECATE

Examples:

  • /aget-enhance-spec NEW specs/AGET_FOO_SPEC.md
  • /aget-enhance-spec UPDATE aget/specs/AGET_SOP_SPEC.md --version 1.2.0
  • /aget-enhance-spec WIRE aget/specs/SKILL_NAMING_CONVENTION_SPEC.md
  • /aget-enhance-spec ADD-REQ aget/specs/AGET_SOP_SPEC.md

Phase Selection

Not all categories require all phases. Use this table to determine which phases to execute:

Category Required Phases
NEW 0, 1, 2, 3, 4, 5, 6 (all)
UPDATE 0, 1, 2, 3, 4, 5, 6 (all)
ADD-REQ 0, 1, 2, 3, 4, 5, 6
WIRE 0, 1, 5, 6
CONSOLIDATE 0, 1, 2, 3, 4, 5, 6 + reference SOP_specification_consolidation.md
DEPRECATE 0, 1, 3, 6

Execution

Step 1: Parse Input

IF no arguments provided:
  Prompt: "What type of enhancement? (NEW, UPDATE, ADD-REQ, WIRE, CONSOLIDATE, DEPRECATE)"
  Prompt: "Path to spec? (leave blank for NEW)"

IF category not in valid list:
  Error: "Invalid category. Valid: NEW, UPDATE, ADD-REQ, WIRE, CONSOLIDATE, DEPRECATE"

IF category in (UPDATE, ADD-REQ, WIRE) AND no spec path:
  Error: "Spec path required for {category} enhancements"

Determine phase list from Phase Selection table above.

Step 2: Phase 0 — Trigger & Diagnosis

Objective: Identify the specification gap and gather evidence.

Execute:

  1. If spec path provided, read the spec file and extract current version, status, requirement count
  2. Search for related L-docs:
    grep -l "<topic_keywords>" .aget/evolution/L*.md
    
  3. Search for related specs:
    ls specs/ aget/specs/ 2>/dev/null | grep -i "<topic>"
    
  4. Document findings as evidence table:
    | Evidence | Source | Impact |
    |----------|--------|--------|
    | <finding> | <L-doc or spec> | <why this matters> |
    

Read the full file on GitHub · 434 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 · 434 lines · 39 tokens per session scan A ba90b6098169

Subscribe to this mod's changes

aget-enhance-spec is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 4,133 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.