Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/.claude/agents/prep-release.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/rajbos/ai-engineering-fluency/prep-release)<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/prep-release"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/prep-release/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/rajbos/ai-engineering-fluency/prep-release"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/prep-release.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 | $0.00051 | $0.05125 |
| Opus 5.5 | $0.00020 | $0.02050 |
| Sonnet 5.5 | $0.00010 | $0.01025 |
| Haiku 4.5 | $0.00005 | $0.00513 |
Grade A, and why
prep-release 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 yesterday.
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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prep Release Agent
Automates the version-bump PR needed before publishing a new release. Detects which of the five releasable components have changed, bumps their version numbers, writes their changelog sections, opens a release-prep branch and PR, and tells the user exactly which GitHub Actions workflows to trigger after merging.
Releasable Components
| Component | Version file | Last release tag prefix | Workflow to run after merge |
|---|---|---|---|
| VS Code extension | vscode-extension/package.json → version |
vscode/v |
release.yml (Actions → Extensions - Release → Run workflow) |
| CLI | cli/package.json → version |
cli/v |
cli-publish.yml (Actions → CLI - Publish to npm and GitHub → Run workflow) |
| Visual Studio extension | visualstudio-extension/src/AIEngineeringFluency/source.extension.vsixmanifest → Identity.Version |
vs/v |
visualstudio-build.yml (Actions → Visual Studio Extension - Build & Package → Run workflow, set publish_marketplace: true) |
| JetBrains plugin | jetbrains-plugin/gradle.properties → pluginVersion |
jetbrains/v |
jetbrains-publish.yml — triggered by pushing a jetbrains/vX.Y.Z tag (see Step 11) |
| Desktop app | desktop/package.json → version |
desktop/v |
desktop-publish.yml — triggered by pushing a desktop/vX.Y.Z tag (see Step 11); a manual run only builds an installer and releases nothing |
Step-by-Step Instructions
Step 1 — Determine the default bump type
If the user didn't specify a bump type, ask:
"What kind of version bump should I apply? (patch / minor / major) — or specify per-component."
Default to patch if the user doesn't specify.
Individual overrides per component are also valid (e.g. "minor for vscode, patch for cli, skip vs").
Step 2 — Find last release tags for each component
Run these five commands to find the most recent release tag for each component:
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.
- yesterday First seen · 345 lines · 51 tokens per session scan A 95c3d7523000
prep-release is an agent published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 5,125 once invoked, about $0.0002 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 2026-10-26.
Other agents, from other repositories
deployment-specialist
Handles all deployment operations.
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
release-executor
Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.
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.