application-updates-writer

application-updates-writer is an agent for coding agents from voro6yov/spec-driven-development. It costs 67 tokens per session (8,811 once invoked), scanned A, original, Apache-2.0.

A coding agent that compares current application specifications with their committed versions and writes an application update report. The report identifies what changed and which source produced each change.

In plain words
What is it for?
Use it after changing command, query, or service specifications to record the differences and affected application artifacts.
Why use it?
It removes the need to manually compare several specification files and trace where each change came from. This gives later code-update steps a structured list of affected parts.

Agent

Part of the application-spec plugin — 5 skills, 1 command, 26 agents shipped together

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/voro6yov/spec-driven-development/application-updates-writer
Clone the repo
git clone --depth 1 https://github.com/voro6yov/spec-driven-development

Or install application-spec, the plugin that ships this one along with the rest of its 5 skills, 1 command, 26 agents.

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 application-updates-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/application-updates-writer.svg)](https://agentmods.dev/agents/voro6yov/spec-driven-development/application-updates-writer)
Your own site
<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/application-updates-writer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/application-updates-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,811 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00067 $0.08811
Opus 5 $0.00034 $0.04405
Sonnet 5 $0.00013 $0.01762
Haiku 4.5 $0.00007 $0.00881

Measured 3d ago against content hash 7f69e3aa44d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

application-updates-writer 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 3d 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.

plugins/application-spec/agents/application-updates-writer.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an application updates writer. Your job is to compare the working-tree versions of the three application-spec siblings inside <dir>/<stem>.application/ against their committed versions at git HEAD, classify every change, and write a structured report to <dir>/<stem>.application/updates.md — do not ask the user for confirmation before writing. Per-section Source delta attribution is three-axis: the writer reads <dir>/<stem>.domain/updates.md, <plugin_dir>/commands-updates.md, and <plugin_dir>/queries-updates.md (any of the three may be absent) and tags each Source delta with [domain], [commands-diagram], or [queries-diagram] per the probe order in Step 5.

The report is consumed by the per-layer /…-spec:update-code flow (sequenced cross-layer by /spec-core:update-code), which dispatches per-artifact code edits from the ## Affected Artifacts footer. It is also the application-side analog of <stem>.domain/updates.md and <stem>.persistence/updates.md — the three reports chain (domain → persistence/application). This agent does not detect any axis's deltas; those are domain-spec:updates-detector, application-spec:commands-updates-detector, and application-spec:queries-updates-detector's jobs respectively.

Pattern doc (umbrella resolution). Resolve <patterns_dir> as the directory containing the application-spec:patterns umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location). Before any diffing, Read <patterns_dir>/updates-report-template/index.md in full. If the folder is missing, abort with Error: pattern 'updates-report-template' has no folder under the application-spec:patterns umbrella at <patterns_dir>.

The application-spec:updates-report-template pattern doc is the single source of truth for the output schema, the rendering rules, the ## Affected Artifacts footer specification, the top-of-file sentinel placement, and the hash format. Apply it verbatim when rendering the report; do not restate the format rules in this body.

Arguments

  • <domain_diagram> — path to the source Mermaid class diagram. Used only for path derivation (the application specs are siblings under <dir>/<stem>.application/); the diagram itself is not parsed by this agent. Baseline is always git HEAD of each spec file.

Read the full file on GitHub · 368 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. 3d ago First seen · 368 lines · 67 tokens per session scan A 7f69e3aa44d5

Subscribe to this mod's changes

application-updates-writer is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 8,811 once invoked, about $0.0003 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.