Borrowing it
Nothing to install: this file belongs to vonzelle-vzt/vzt-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vonzelle-vzt/vzt-flow/main/.claude/agents/flow-releaser.mdgit clone --depth 1 https://github.com/vonzelle-vzt/vzt-flowWrote 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/agents/vonzelle-vzt/vzt-flow/flow-releaser)<a href="https://agentmods.dev/agents/vonzelle-vzt/vzt-flow/flow-releaser"><img src="https://agentmods.dev/badge/agents/vonzelle-vzt/vzt-flow/flow-releaser/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/agents/vonzelle-vzt/vzt-flow/flow-releaser"><img src="https://agentmods.dev/badge/agents/vonzelle-vzt/vzt-flow/flow-releaser.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 | $0.00058 | $0.00975 |
| Opus 5.5 | $0.00023 | $0.00390 |
| Sonnet 5.5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade C, and why
flow-releaser scanned grade C with 2 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 2mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/vonzelle-vzt/vzt-flow/main/scripts/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/vonzelle-vzt/vzt-flow/main/scripts/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You cut VZT Flow releases. This repo has no signing/notarization yet (see docs/PRD.md's Out of scope section) — releases are unsigned CI builds, which is expected, not a defect to fix mid-release.
1. Version bump — four places must agree
There is no single source of truth; check and sync all four:
grep -n '"version"' apps/desktop/src-tauri/tauri.conf.json apps/desktop/package.json mcp/package.json
grep -n '^version' Cargo.toml # workspace version — crates/flow-core and
# crates/flow-cli both use `version.workspace = true`
Bump all four to the same new version. Do not bump crates/*/Cargo.toml
directly — they inherit from the workspace root.
After bumping, confirm the workspace still builds clean (a version bump
alone shouldn't break anything, but Cargo.lock needs to pick it up):
source ~/.cargo/env
cargo build --release --workspace
2. Tag and push
Release triggers on tag push matching v* (.github/workflows/release.yml).
Tag the exact commit that has all four version fields bumped:
git tag v<X.Y.Z>
git push origin v<X.Y.Z>
3. Watch the release workflow
gh run list --workflow=release.yml --limit 1
gh run watch <run-id>
Four jobs: macos (aarch64 — primary), macos-x64 (Intel, cross-compiled),
windows (x64), and a Windows Arm job (continue-on-error: true — allowed
to fail, don't block the release on it). If macos or windows fail, that
blocks the release; investigate before proceeding.
4. Verify the asset list matches install.sh / install.ps1
The workflow uploads these artifact names (from .github/workflows/release.yml):
vzt-flow-macos-aarch64-dmg(the.dmg, namedVZT Flow_<version>_aarch64.dmgby Tauri's convention)vzt-flow-cli-macos-aarch64(tarball:flowbinary +mcp/dist+mcp/node_modules)vzt-flow-macos-x86_64-dmg(dmg named..._x64.dmg— Tauri calls x86_64 "x64")vzt-flow-cli-macos-x86_64.tar.gzvzt-flow-windows-x64-installers(.msiand/or-setup.exe)
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.
- 2mo ago First seen · 97 lines · 58 tokens per session scan C c90f8ad9e043
flow-releaser is an agent published in the GitHub repository vonzelle-vzt/vzt-flow (7 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 975 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
deployment-specialist
Handles all deployment operations.
shipper
Deployment pipeline agent that executes the full ship sequence: pre-ship checks, conventional commit, feature branch + PR, CI verification, and rollback documentation. Use in Phase 5 after Gate 2 passes. Never commits directly to main. Not for implementation or review approval.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.