aid-define

aid-define is a skill for Claude Code from AndreVianna/aid-methodology. It costs 108 tokens per session (2,735 once invoked), scanned A, original, MIT.

A skill for splitting approved software requirements into separate features recorded in REQUIREMENTS.md. It also checks those features against the project's knowledge base and codebase before they are specified for implementation.

In plain words
What is it for?
Use it after `/aid-describe` has produced approved requirements and before `/aid-specify`; it creates feature sections and cross-references them with existing project information.
Why use it?
It turns a large approved request into smaller units with linked acceptance criteria, reducing ambiguity before detailed design begins.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it after /aid-describe has produced approved requirements and before /aid-specify; it creates feature sections and cross-references them with existing project information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrevianna/aid-methodology/aid-define
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 AndreVianna/aid-methodology --skill aid-define
Clone the repo
git clone --depth 1 https://github.com/AndreVianna/aid-methodology

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 aid-define

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-define/github.svg)](https://agentmods.dev/skills/andrevianna/aid-methodology/aid-define)
Your own site
<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-define"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-define/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 aid-define

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-define"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-define.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,735 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

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 →

  • medium Excessive Agency · line 164
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00108 $0.02735
Opus 5.5 $0.00043 $0.01094
Sonnet 5.5 $0.00022 $0.00547
Haiku 4.5 $0.00011 $0.00274

Measured 26d ago against content hash 308c2cc9e074, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aid-define 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 26d 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.

.agents/skills/aid-define/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Definition from Approved Requirements

Agents Involved

aid-define is multi-agent — different states use different agents.

State Phase Agent Why
5 FEATURE-DECOMPOSITION Feature Decomposition aid-architect Design work — breaking requirements into structured features
6 CROSS-REFERENCE Cross-Reference & Refine aid-reviewer Adversarial validation against KB and codebase
7 DONE DONE (no dispatch) Terminal state, user choice prompt

Decompose approved REQUIREMENTS.md into ### Feature NNN sections under § 11, then cross-reference the result against the Knowledge Base and codebase. Produces REQUIREMENTS.md §11 feature sections ready for /aid-specify.

Precondition: ## Interview State: Approved must be present in .aid/works/{work}/STATE.md. If requirements are not yet approved, run /aid-describe {work} first to gather and approve requirements.

Workspace structure:

.aid/
  knowledge/           <- shared KB (populated by /aid-discover)
  work-001-name/
    STATE.md           <- process (Interview State: Approved, Cross-Reference, Features State)
    REQUIREMENTS.md    <- approved requirements (/aid-describe) + §11 Features
                          (this skill) + each feature's Technical Specification
                          (/aid-specify). Features are sections; they have no
                          folders and no files of their own.

State keys. interview.state/interview.grade/interview.sections[] and features[] are real keys in work-state-template.yml -- this skill creates one features[] entry per ### Feature NNN section it appends to REQUIREMENTS.md § 11, and /aid-specify updates it as each feature advances. A per-feature "Cross-Reference" status and a Q&A-adjacent "Review History" list, as used below, do still carry no dedicated key -- they describe this skill's aspirational tracking design rather than a writable structure, and that remains an open schema gap. The Review History list now has a real target of its own, the review_history sequence, and Cross-phase Q&A entries have the qa sequence.

Read the full file on GitHub · 249 lines

Files

What ships with it

6 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. 26d ago Changed 308c2cc9e074
  2. 1mo ago Changed · -2 lines 331442a15186
  3. 2mo ago Changed · +3 lines 783c8249a1d1
  4. 2mo ago First seen · 248 lines · 108 tokens per session scan A 965bf2435c77

Subscribe to this mod's changes

aid-define is a skill published in the GitHub repository AndreVianna/aid-methodology (6 stars, last pushed 11d ago), licensed MIT. It adds 108 tokens to every session and 2,735 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.

Related

aid-define compared with skills from other repositories

aid-define next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aid-defineAndreVianna/aid-methodologySkill611d agoMITA108Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code