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-discoverWrote 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-discover)<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-discover"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-discover/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-discover"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-discover.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 | $0.00118 | $0.05595 |
| Opus 5 | $0.00059 | $0.02797 |
| Sonnet 5 | $0.00024 | $0.01119 |
| Haiku 4.5 | $0.00012 | $0.00560 |
Grade A, and why
aid-discover 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 8d 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brownfield Project Discovery
Analyze an existing project repository — all code, configuration, and documentation — and
produce a structured .aid/knowledge/ directory by orchestrating 5 specialized discovery subagents.
Includes a built-in quality gate that reviews, grades, and fixes KB documents.
State machine — each /aid-discover invocation drives the state machine until it hits a natural pause point per .claude/aid/templates/state-machine-chaining.md. Mechanical states and inline-question states auto-chain; only PAUSE-FOR-USER-ACTION, PAUSE-FOR-USER-DECISION, and HALT stop the run.
⛔ PRIME DIRECTIVE: NO ASSUMPTIONS — DEFER TO THE USER
This rule governs every state, every sub-agent, and the orchestrator itself. It overrides convenience, speed, and confidence.
Discovery's job is to report what the project actually is, never what an agent guesses it is. So whenever ANYTHING is unclear, ambiguous, contradictory, or a judgment call — an undefinable term, a discrepancy between two sources, an uncertain classification, which of two things is authoritative, in-or-out-of-scope, how to resolve a conflict — DO NOT resolve it by assumption. Record a question and DEFER the decision to the user.
- A
LIKELY/UNCERTAIN/probably/ "I'll assume" answer written into the KB is a FAILURE, not a finding. Turn it into a Q&A entry. - Never silently reconcile a contradiction — record both sides and ask which is right.
- State a fact only when you can ground it from the artifacts with certainty (cite the source). Otherwise, ASK.
The deferral machinery is already built in — use it: the Step 0cx (domain), 0d (doc-set),
0f (path), and Step 5c (term-exclusion) gates are PAUSE-FOR-USER-DECISION points; sub-agents
write open questions to .aid/knowledge/.scout-questions.tmp; Step 6b consolidates them into
STATE.md ## Q&A (Pending); and the Q-AND-A state resolves them with the user before
approval. Every disambiguation flows through this path — none is decided silently.
What ships with it
18 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/agent-prompts.md 29 KB
- references/doc-set-resolve.md 20 KB
- references/document-expectations.md 41 KB
- references/path-config.md 5.7 KB
- references/reviewer-brief.md 8.0 KB
- references/reviewer-prompt-actback.md 11 KB
- references/reviewer-prompt-anatomy.md 12 KB
- references/reviewer-prompt-correctness.md 6.5 KB
- references/reviewer-prompt-teachback.md 11 KB
- references/reviewer-prompt.md 2.6 KB
- references/state-approval.md 1.9 KB
- references/state-closure.md 18 KB
- references/state-done.md 3.3 KB
- references/state-elicit.md 20 KB
- references/state-fix.md 7.1 KB
- references/state-generate.md 55 KB
- references/state-q-and-a.md 3.3 KB
- references/state-review.md 34 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.
- 8d ago First seen · 387 lines · 118 tokens per session scan A db80ab3eef6a
aid-discover is a skill published in the GitHub repository AndreVianna/aid-methodology (5 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 5,595 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 2026-09-03.
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…