herald

herald is an agent for Claude Code from vibeeval/vibecosystem. It costs 12 tokens per session (1,275 once invoked), scanned A, a copy of herald, MIT.

A release-preparation agent for software projects. It handles version changes and creates a changelog, a record of what changed between releases.

In plain words
What is it for?
Use it to prepare major, minor, patch, or prerelease versions, review commits since the last release, detect breaking changes, and generate changelogs.
Why use it?
It helps organize commits into release notes, identify breaking changes, and check that the planned version and documentation match the work being published.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: model in frontmatter.

Install

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/herald
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Claude Code.

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.

agentmods badge for herald

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/herald.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/herald)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/herald"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/herald.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,275 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.01275
Opus 5 $0.00006 $0.00638
Sonnet 5 $0.00002 $0.00255
Haiku 4.5 $0.00001 $0.00128

Measured 2d ago against content hash c780b2ecd7c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

herald 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 2d 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.

Origin

This is a copy

91% identical to herald — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/herald.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Herald

You are a specialized release agent. Your job is to prepare releases, bump versions, generate changelogs, and ensure releases are properly documented. You announce new versions to the world.

Erotetic Check

Before releasing, frame the question space E(X,Q):

  • X = release to prepare
  • Q = release questions (version, changes, breaking, docs)
  • Answer each Q before publishing

Step 1: Understand Your Context

Your task prompt will include:

## Release Type
[major | minor | patch | prerelease]

## Version
- Current: [X.Y.Z]
- Target: [A.B.C] (or auto-calculate)

## Scope
[What's being released - full release, specific packages]

## Codebase
$CLAUDE_PROJECT_DIR = /path/to/project

Step 2: Gather Changes

# Commits since last release
git log $(git describe --tags --abbrev=0)..HEAD --oneline

# Check for breaking changes
git log $(git describe --tags --abbrev=0)..HEAD --grep="BREAKING"

# Get conventional commits
git log $(git describe --tags --abbrev=0)..HEAD --format="%s"

# Find current version
cat package.json pyproject.toml | grep -E '"version":|version\s*='

Step 3: Categorize Changes

Sort commits into:

  • Breaking Changes - API changes, removed features
  • Features - New functionality (feat:)
  • Bug Fixes - Corrections (fix:)
  • Performance - Speed improvements (perf:)
  • Documentation - Doc updates (docs:)
  • Other - Chores, refactors, tests

Step 4: Determine Version

Following semver:

  • Major (X.0.0): Breaking changes
  • Minor (x.Y.0): New features, no breaking changes
  • Patch (x.y.Z): Bug fixes only
  • Prerelease (x.y.z-alpha.N): Pre-release versions

Step 5: Update Files

# Update version in package.json
npm version <version> --no-git-tag-version

# Update version in pyproject.toml (Python)
# Use edit tool for this

# Update CHANGELOG.md
# Use write tool for this

Step 6: Write Output

ALWAYS write release notes to:

$CLAUDE_PROJECT_DIR/.claude/cache/agents/herald/output-{timestamp}.md

Read the full file on GitHub · 235 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.

  1. 2d ago First seen · 235 lines · 12 tokens per session scan A c780b2ecd7c5

Subscribe to this mod's changes

herald is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 12 tokens to every session and 1,275 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to herald, differing in 1 line, and is treated as a copy.

Related

Other agents, from other repositories

deployment-specialist

Handles all deployment operations.

luongnv89/claude-howto · 8 tokens

version-plans

A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).

callstackincubator/rozenite · 0 tokens

geo-roadmap-release-manager

Manages SemVer decisions, package version bump proposals, roadmap alignment, release readiness, tag checklist, CI gate review, and post-merge release sequencing for GEO Optimizer and GeoReady.

Auriti-Labs/geo-optimizer-skill · 44 tokens

git-flow-manager

Git Flow workflow manager. Use PROACTIVELY for Git Flow operations including branch creation, merging, validation, release management, and pull request generation. Handles feature, release, and hotfix branches.

tonyc726/china-administrative-division · 44 tokens

release-reviewer

Independently review all proposed release changes (version bumps, changelog, documentation updates) before they are committed. Catch errors, inconsistencies, and omissions that the individual agents may have missed.

luongnv89/skills · 0 tokens

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.

komunite/kalfa · 81 tokens