A trigger-based workflow for a VDT drain session, started when the owner writes «абракадабра». It first asks whether to work on PoolAI or GSV, then follows the selected project's documented workflow.

Use it to run the documented VDT drain process for either the PoolAI or GSV project, including project scanning, review, testing, and delivery.

It provides a defined sequence for choosing the project, scanning it, draining pending work, testing, and creating one commit and push.

How platinoff/poolAI configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to platinoff/poolAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/platinoff/poolAI/main/.agents/skills/abracadabra/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/platinoff/poolAI

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/platinoff/poolai/abracadabra.svg)](https://agentmods.dev/skills/platinoff/poolai/abracadabra)

Your own site

<a href="https://agentmods.dev/skills/platinoff/poolai/abracadabra"><img src="https://agentmods.dev/badge/skills/platinoff/poolai/abracadabra.svg" alt="Measured on agentmods" height="20"></a>

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,337 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00100	$0.01337
Opus 5	$0.00050	$0.00668
Sonnet 5	$0.00020	$0.00267
Haiku 4.5	$0.00010	$0.00134

Measured 8d ago against content hash b280ce63232d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

abracadabra 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.

.agents/skills/abracadabra/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

«абракадабра» — VDT drain session (PoolAI fallback)

Git canon: S:\rust\GSV\.agents\skills\abracadabra\. Kit: S:/rust/GSV/docs/gsv/GSV_VDT_KIT.md. Registry: S:/rust/GSV/docs/gsv/PRODUCTS.md. Prefer File → Open Folder → S:\rust\GSV (or gsv.code-workspace). This file remains so a PoolAI-only window can still route.

Works the same in Cursor and OpenCode. Client copies under .cursor/skills/ and .opencode/skills/ must stay identical in the open workspace.

Step 0 — Choose the project (ALWAYS first)

When the owner writes абракадабра, before anything else ask which project to drain. Use the host question UI (one click, two options):

Cursor: AskQuestion
OpenCode: question

Option	Project	Canon docs	Flow
poolai	PoolAI (repo root, `src/`, `tests/`)	`docs/development/NEXT_SESSION_PROMPT.md`, `docs/catalog/FUNCTION_MANAGEMENT.md` §5.12	S0 disk → project scan → drain band (FM §5.12) → vision close → test → one commit + push
gsv	GSV (`S:\rust\GSV` — separate git repo)	`S:/rust/GSV/docs/NEXT_SESSION_PROMPT.md`, `S:/rust/GSV/docs/GSV_ROLES.md`, `S:/rust/GSV/docs/gsv/GSV_TECH_ROADMAP.md`	S0 disk (GSV target) → project scan (warnings first) → drain next band (`GSV_TECH_ROADMAP`) → Speeds + Rust panel → `gsv-vision-sync` → one commit (+ push if remote exists)

poolai flow

S0 disk: df -h /s + bash scripts/check_target_disk.sh → cargo clean if needed → git fetch → HANDOFF → FM §1–§5.1 → NEXT_SESSION → poolai-vision-sync --check ok.
Project scan (if §5.12 < 10): warnings/diagnostics first (rust_diagnostics.json, clippy warnings, compile errors) → concept → FM §5.1 → architect → roadmaps → gaps → code → 10 PH-S* into §5.12.
Drain all open PH-S* (no mid-drain push).
Vision close: FM §5.12 ✅ + HANDOFF + NEXT → one poolai-vision-sync → rev from manifest → --check.
Test: one cargo fmt --all → one cargo test-ci → record-test-ci-speed.sh + record-rust-diagnostics.sh.
Git (end of session): one commit → git push origin main + summary in chat.

Read the full file on GitHub · 71 lines

Changes

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 · 71 lines · 100 tokens per session scan A b280ce63232d

Subscribe to this mod's changes

abracadabra is a skill published in the GitHub repository platinoff/poolAI (4 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,337 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 2026-08-31.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

poolAI: Skill for Claude Code