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.
npx skills add AndreVianna/aid-methodology --skill aid-specifygit clone --depth 1 https://github.com/AndreVianna/aid-methodologyWrote 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-specify)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00099 | $0.02779 |
| Opus 5 | $0.00049 | $0.01389 |
| Sonnet 5 | $0.00020 | $0.00556 |
| Haiku 4.5 | $0.00010 | $0.00278 |
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 6d 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 — 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 inwork-state-template.yml, one entry per feature, created by/aid-defineat 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 theSTATE.md->STATE.ymlconverter 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'sqakey 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 noqakey at the work level at all (full-layout omission rule), and/aid-specifyruns 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: writefeatures[]entries for real.
What ships with it
9 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/handling-outcomes.md 1.3 KB
- references/known-issues-scope.md 2.4 KB
- references/reviewer-brief.md 6.7 KB
- references/state-blocked.md 1.1 KB
- references/state-continue.md 5.0 KB
- references/state-done.md 615 B
- references/state-initialize.md 8.1 KB
- references/state-review.md 4.2 KB
- references/state-spike.md 1.2 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.
- 6d ago Changed · +3 lines 42e204b569a1
- 9d ago First seen · 269 lines · 99 tokens per session scan A 782132b3f759
aid-specify is a skill published in the GitHub repository AndreVianna/aid-methodology (5 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 2,779 once invoked, about $0.0005 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…