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-create-stackgit 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-create-stack)<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-create-stack"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-create-stack/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-create-stack"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-create-stack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00191 | $0.01974 |
| Opus 5.5 | $0.00076 | $0.00790 |
| Sonnet 5.5 | $0.00038 | $0.00395 |
| Haiku 4.5 | $0.00019 | $0.00197 |
Grade A, and why
aid-create-stack 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 25d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Stack (realize a seed into the C0 document)
Bind VERB=create, ARTIFACT=stack -- the create stage in the contract's
vocabulary -- then follow the shared contract at
.aid/runtime/templates/design-lifecycle.md. This skill binds that contract and restates
none of its rules. It consumes the seed /aid-design-stack produces and touches
.aid/design/ for no other purpose.
- Boundary vs
/aid-update-stack: that skill revises C0 content this lifecycle already committed; this one realizes a seed. - Boundary vs
/aid-create-configand/aid-update-config: those act on a configuration option within a chosen stack; this one records the stack choice itself. - Not a numbered pipeline phase; does not route to
/aid-execute.
State machine: INTAKE -> CREATE -> VERIFY -> PRESENT -> DONE, as
design-lifecycle.md § Skill shape defines it. Print the [State: NAME] -- {purpose} entry
line on each state.
State: INTAKE
- Allocate through the Work Initiation Gate exactly as the contract's Allocation rule
requires (
.agents/skills/aid-design/SKILL.mdINTAKE step 4 is the shape), withinitiator: aid-create-stack.phaseis not driven. - Read the seed at
.aid/design/stack.md. - Resolve the destination by concern, not filename. This skill binds concern C0
(technology,
.aid/runtime/templates/kb-authoring/concern-model.md). The seed's## Destinationnames the resolved path; where it does not, resolve C0 against.aid/settings.ymlknowledge.doc_set, falling back to the C0 row of.aid/runtime/templates/kb-authoring/domain-doc-matrix.md, and confirm with the user. An ambiguous realization is asked, never picked silently. The seed also names a second destination -- the project's D document, for the rejected alternatives. - Read the whole destination if it exists, and note its
source:field. - Classify complexity for the
aid-architectdispatch (verifier tier >= producer).
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.
- 25d ago Changed a40740ef7e79
- 2mo ago First seen · 175 lines · 191 tokens per session scan A 237db8b878ed
aid-create-stack is a skill published in the GitHub repository AndreVianna/aid-methodology (6 stars, last pushed 10d ago), licensed MIT. It adds 191 tokens to every session and 1,974 once invoked, about $0.0008 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.
aid-create-stack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aid-create-stackAndreVianna/aid-methodology | Skill | 6 | 10d ago | MIT | A | 191 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |