Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AndreVianna/aid-methodologynpx agentmods add skills/andrevianna/aid-methodology/aid-describeWrote 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.
[](https://agentmods.dev/skills/andrevianna/aid-methodology/aid-describe)<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-describe"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-describe/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.
<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-describe"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-describe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00119 | $0.04060 |
| Opus 5 | $0.00060 | $0.02030 |
| Sonnet 5 | $0.00024 | $0.00812 |
| Haiku 4.5 | $0.00012 | $0.00406 |
Grade A, and why
aid-describe 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversational Requirements Gathering
State machine: FIRST-RUN -> Q-AND-A -> CONTINUE -> {greenfield: DESCRIBE-SEED ->} COMPLETION [PAUSE -> /aid-define].
Agents Involved
aid-describe is multi-agent — different states use different agents.
| State | Phase | Agent | Why |
|---|---|---|---|
| 1–4 | Conversational interview | aid-interviewer |
Empathetic dialogue, deterministic advancing |
| DESCRIBE-SEED | Greenfield KB seed authoring (aid-describe step per D3) | aid-interviewer + dispatches aid-reviewer for step 5 |
Engine-driven 5-element seed elicitation + doc authoring + coherence check + greenfield-mode review gate |
The frontmatter default agent: aid-interviewer covers States 1–4. DESCRIBE-SEED also uses aid-interviewer, additionally dispatching aid-reviewer for its step 5 greenfield-mode review gate.
Gather requirements from a human stakeholder through the seasoned-analyst elicitation
engine (references/elicitation-engine.md): one fixed D1 opener followed by a
deterministic five-step next-move selector that adapts each question to the current gap,
calibration state, and move playbook (references/move-playbook.md,
references/calibration.md, references/advisor-stance.md). One question per turn.
Builds REQUIREMENTS.md incrementally -- each confirmed answer updates the document
immediately.
Workspace structure:
.aid/
knowledge/ <- shared KB (populated by /aid-discover)
work-001-name/ <- one work = one interview cycle
STATE.md <- process (§§ Interview State, Cross-phase Q&A, Features State...)
REQUIREMENTS.md <- product (clean document, only project information)
features/ <- product (one folder per feature, created by /aid-define)
feature-001-name/
# § 11 feature sections gain their technical specification
# when /aid-specify runs
First run: Conversational interview from scratch.
Subsequent runs (before approval): Resume interview for incomplete sections.
After approval: Approved REQUIREMENTS.md is ready — run /aid-define {work} to decompose into features.
Loopback: Process Q&A injected by downstream phases (e.g., /aid-specify).
What ships with it
13 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.
- references/advisor-stance.md 13 KB
- references/calibration.md 8.1 KB
- references/coherence-check.md 13 KB
- references/elicitation-engine.md 20 KB
- references/interview-loop.md 2.4 KB
- references/interview-strategies.md 4.4 KB
- references/kb-hydration.md 4.8 KB
- references/move-playbook.md 14 KB
- references/state-completion.md 6.8 KB
- references/state-continue.md 2.1 KB
- references/state-describe-seed.md 28 KB
- references/state-first-run.md 5.1 KB
- references/state-q-and-a.md 2.0 KB
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.
- 11d ago First seen · 311 lines · 119 tokens per session scan A 2bae84bbe1db
aid-describe is a skill published in the GitHub repository AndreVianna/aid-methodology (5 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 4,060 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…