CHANGELOG

// Before (no longer compiles) d.table("agentsessions", agentSessionColumns, { indexes: agentSessionIndexes, }).

Agent

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/vertz-dev/vertz/changelog
Clone the repo
git clone --depth 1 https://github.com/vertz-dev/vertz
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,070 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04070
Opus 5 $0.00000 $0.02035
Sonnet 5 $0.00000 $0.00814
Haiku 4.5 $0.00000 $0.00407

Measured today against content hash 33e82e16321e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CHANGELOG 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 today.

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.

packages/agents/CHANGELOG.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@vertz/agents

0.2.80

Patch Changes

  • #2997 5bf64f2 Thanks @viniciusdacal! - BREAKING: agentSessionColumns / agentMessageColumns are now functions — call them (...agentSessionColumns()), don't spread the bare identifier.

    // Before (no longer compiles)
    d.table("agent_sessions", agentSessionColumns, {
      indexes: agentSessionIndexes,
    });
    
    // After (default behavior unchanged — still d.text() on disk)
    d.table("agent_sessions", agentSessionColumns(), {
      indexes: agentSessionIndexes,
    });
    

    Closes #2958.

    Pass { useJsonb: true } with a generic to opt each column into d.jsonb<T>(), which emits JSONB on Postgres (indexable, typed operators) and stays TEXT on SQLite (the driver auto-parses on read):

    d.table(
      "agent_sessions",
      agentSessionColumns<AgentState>({ useJsonb: true }),
      { indexes: agentSessionIndexes }
    );
    
    // Entity reads now return AgentState, not string.
    const { items } = await ctx.entities["agent-session"].list({});
    items[0]?.state.step; // typed
    

    The AgentStore path (sqliteStore / d1Store) is orthogonal — it keeps its own JSON.stringify / JSON.parse wrapping and writes raw SQL, so on SQLite the on-disk shape is the same in both modes and store/entity readers share rows without coordination.

  • #2966 6181b03 Thanks @viniciusdacal! - feat(agents): bridge AgentStore with Vertz entities for RLS-aware queries [#2847]

    Adds @vertz/agents/entities subpath exporting column packs (agentSessionColumns, agentMessageColumns, agentSessionIndexes, agentMessageIndexes) and a defineAgentEntities(db) factory that turns the store's tables into first-class Vertz entities. App-side reads via /api/agent-session routes or ctx.entities.agentSession.list() now flow through the CRUD pipeline with full rules.* enforcement (auth, tenant scoping, row-level where). Writes from the agent loop keep going through sqliteStore/d1Store — same atomic paths, unchanged hot path.

Read the full file on GitHub · 242 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. today First seen · 242 lines · 0 tokens per session scan A 33e82e16321e

Subscribe to this mod's changes

CHANGELOG is an agent published in the GitHub repository vertz-dev/vertz (45 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,070 tokens. 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 2026-09-01.

Related

Other agents, from other repositories

switchboard

This project uses the Switchboard protocol for cross-IDE agent collaboration.

open-wa/wa-automate-nodejs · 0 tokens

docs-freshness-checker

Checks if documentation is stale by comparing doc pages against the actual source code. Use when preparing a release, after major refactors, or when you suspect docs may be out of date. Finds documentation that references APIs, features, or patterns that have changed in the source code.

BrainDAO/adk-ts · 62 tokens

mcp-docs-generator

Generates complete MCP server documentation pages. Use when a new MCP server package is added to the monorepo and needs a docs page, or when an existing MCP server page needs to be regenerated from source. Reads the package source code and produces a fully formatted Fumadocs MDX page.

BrainDAO/adk-ts · 66 tokens

docs-reviewer

Reviews documentation pages and READMEs for quality, accuracy, and style guide compliance. Use proactively after writing or editing any documentation, README, or MDX file. Also use when reviewing PRs that touch docs.

BrainDAO/adk-ts · 47 tokens

docs-writer

Writes and updates documentation pages for the ADK-TS docs site. Use when creating new doc pages, rewriting existing pages, adding new sections, or updating content to match source code changes. Reads source code and existing docs to produce complete, production-ready Fumadocs MDX pages.

BrainDAO/adk-ts · 62 tokens

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

chenxin-yan/crust · 0 tokens