aid-specify

aid-specify is a skill for Claude Code from AndreVianna/aid-methodology. It costs 99 tokens per session (2,770 once invoked), scanned A, original, MIT.

A collaborative technical-specification tool for deciding how one defined feature should be built within an existing codebase.

In plain words
What is it for?
Use it to refine architecture, review technical choices against the project, and document one feature's implementation.
Why use it?
It turns a feature definition into an agreed implementation approach before the work is broken into tasks.

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 to refine architecture, review technical choices against the project, and document one feature's implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrevianna/aid-methodology/aid-specify
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-specify
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-specify

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-specify"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-specify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,770 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 high

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 →

  • high Memory Poisoning · line 155
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 $0.00099 $0.02770
Opus 5.5 $0.00040 $0.01108
Sonnet 5.5 $0.00020 $0.00554
Haiku 4.5 $0.00010 $0.00277

Measured 26d ago against content hash f33e00c169fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aid-specify 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-specify/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Specification — Conversational Refinement

Specify the technical implementation of a single feature through conversational refinement with the user.

The agent is a tech lead, not an interviewer. It proposes concrete solutions grounded in the existing architecture. The user validates, redirects, or deepens the discussion.

One feature at a time. The feature path is a required argument.

The Loop:

Every section follows the same cycle:

1. PROPOSE  → agent proposes (grounded in KB, codebase, SPEC)
2. DISCUSS  → user and agent refine together
3. WRITE    → save what was agreed into REQUIREMENTS.md §11 / Feature NNN
4. REVIEW   → grade what was written against KB/codebase reality
             → pass? next section. fail? back to 1.

Re-run = enter at step 4 with existing content.

Workspace:

.aid/
  knowledge/               ← shared KB
  work-NNN-{name}/
    STATE.yml              ← process (features sequence, qa sequence)
    REQUIREMENTS.md        ← product: §11 Features holds one section per
                              feature (decomposition from /aid-define +
                              Technical Specification from here). Features have
                              no folders and no files of their own.

Accuracy note. Features State is AUTHORED, and it now has a real target: the features: sequence in work-state-template.yml, one entry per feature, created by /aid-define at decomposition and updated here as each feature advances. It carried no key and was documented as a read-only DERIVED view for as long as this note said so, which was wrong twice over -- nothing derives it, and the mislabel made the STATE.md -> STATE.yml converter treat a real row as proof that a work predated the per-unit hierarchy, so it refused every work that had been through /aid-define. Cross-phase Q&A's qa key is AUTHORED only at the delivery level (delivery-state-template.yml) or, on the flattened Lite path, at the work level (work-state-template.yml) -- a full-path work has no qa key at the work level at all (full-layout omission rule), and /aid-specify runs before any delivery exists (Specify precedes Plan), so a full-path work has no delivery yet to hold one either -- that half of the gap is unchanged and is still a candidate follow-up. The Features State half is closed: write features[] entries for real.


Read the full file on GitHub · 272 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. 26d ago Changed f33e00c169fd
  2. 2mo ago Changed · +3 lines 42e204b569a1
  3. 2mo ago First seen · 269 lines · 99 tokens per session scan A 782132b3f759

Subscribe to this mod's changes

aid-specify is a skill published in the GitHub repository AndreVianna/aid-methodology (6 stars, last pushed 11d ago), licensed MIT. It adds 99 tokens to every session and 2,770 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 2026-09-03.

Related

aid-specify compared with skills from other repositories

aid-specify next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aid-specifyAndreVianna/aid-methodologySkill611d agoMITA99Claude 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