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-ticketgit 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-ticket)<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-create-ticket"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-create-ticket/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-ticket"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-create-ticket.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 | $0.00140 | $0.03629 |
| Opus 5.5 | $0.00056 | $0.01452 |
| Sonnet 5.5 | $0.00028 | $0.00726 |
| Haiku 4.5 | $0.00014 | $0.00363 |
Grade A, and why
aid-create-ticket 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.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Ticket
/aid-create-ticket files a new ticket in a catalogued (or host-owned) issue tracker after
previewing the exact payload and gaining an explicit confirm. It is one of three peer, on-demand
ticket skills — alongside /aid-read-ticket and /aid-update-ticket — that give AID users a
tool-agnostic way to interact with whatever tracker their project has integrated.
Shared reference. The connector-resolution ladder, the grammar-parse rules, the write
preview/confirm-gate convention, Level Resolution, and Parent Resolution this skill uses are all
described once, in
ticket-resolution.md. This SKILL.md
never restates any of that — each state below points to the relevant section instead.
Absent from the mandatory pipeline flow. Like /aid-ask and /aid-set-connector, this is
an optional, on-demand utility skill outside the Discover-Execute flow: no phase gate references
it, no shortcut-catalog.yml entry, no work-NNN scaffold, no STATE.yml of its own — invoked
directly by name.
State-machine chaining: each /aid-create-ticket invocation drives the state machine —
PARSE-ARGS → RESOLVE-CONNECTOR → COMPOSE → LEVEL-RESOLVE → CONFIRM → FILE → RETURN-REF — until
it hits a natural pause point per
.aid/runtime/templates/state-machine-chaining.md.
CONFIRM's AskUserQuestion exchange is fully inline, so it is a CHAIN advance, never
PAUSE-FOR-USER-DECISION — a single invocation runs every state through to RETURN-REF (or an
earlier stop/cancel) without exiting mid-run to collect an answer.
Read-only until CONFIRM. RESOLVE-CONNECTOR, COMPOSE, and LEVEL-RESOLVE only ever read —
the tracker's issue-type list is queried (a non-destructive read), never written. Nothing about
the level, the parent, or the rest of the payload reaches the tracker until the user explicitly
confirms at CONFIRM; FILE is the only state that writes, and it writes exactly once, right
after that confirm.
Writes no local file. This skill's only external effect is the host-MCP ticket file (FILE
state, gated behind confirm) — there is no Write/Edit tool in allowed-tools, and no file
under this repo is ever touched: the three ticket skills persist nothing locally.
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.
- 26d ago Changed 1f0147e16f1d
- 2mo ago First seen · 261 lines · 140 tokens per session scan A 3d8540dc35fb
aid-create-ticket is a skill published in the GitHub repository AndreVianna/aid-methodology (6 stars, last pushed 11d ago), licensed MIT. It adds 140 tokens to every session and 3,629 once invoked, about $0.0006 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-ticket compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aid-create-ticketAndreVianna/aid-methodology | Skill | 6 | 11d ago | MIT | A | 140 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |