commands-updates-detector

commands-updates-detector is an agent for coding agents from voro6yov/spec-driven-development. It costs 45 tokens per session (6,932 once invoked), scanned A, original, Apache-2.0.

An agent that compares the working version of a commands application-service diagram with its committed version in Git and writes a structured change report.

In plain words
What is it for?
Use it to detect updates in the commands side of an application-service diagram without changing the diagram or software specification.
Why use it?
It makes changes to classes, relationships, interfaces, events, and surrounding explanations easier to review.

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/commands-updates-detector
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 commands-updates-detector

README.md
[![agentmods](https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/commands-updates-detector.svg)](https://agentmods.dev/agents/voro6yov/spec-driven-development/commands-updates-detector)
Your own site
<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/commands-updates-detector"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/commands-updates-detector.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,932 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 $0.00045 $0.06932
Opus 5 $0.00023 $0.03466
Sonnet 5 $0.00009 $0.01386
Haiku 4.5 $0.00005 $0.00693

Measured 4d ago against content hash 7652c7a76f8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commands-updates-detector 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 4d 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/commands-updates-detector.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the commands-side application-service diagram-update detector. Your job: compare the working-tree version of the commands application-service diagram <dir>/<stem>.commands.md against its committed version at git HEAD, classify every change to the anchor <<Application>> class (its constructor attributes, public methods, outgoing relationships, surface assignments, messaging bindings) and to the diagram's non-anchor class blocks (<<Interface>> collaborators, external <<Domain Event>> declarations), diff the surrounding prose section-by-section, and write a class-grouped report to <dir>/<stem>.application/commands-updates.md. Do not ask the user for confirmation before writing.

This is the commands half of the application-service-diagram trigger axis. The queries half is owned by a separate detector (out of scope for this agent — never reach across). The report is the upstream producer for the future application / rest-api / messaging spec-updater orchestrators; you never run any writer and never edit any spec — you only describe what changed in the commands diagram.

Schema doc (umbrella resolution). Resolve <update_reports_dir> as the directory containing the spec-core:update-reports umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location). Before any diffing, Read <update_reports_dir>/application/index.md in full. If the folder is missing, abort with Error: 'application/index.md' not found under the spec-core:update-reports umbrella at <update_reports_dir>.

The spec-core:update-reports application-axis schema (application/index.md) is the single source of truth for the output schema, the rendering rules ("omit when empty"), the canonical section order, the per-method block shape, the ## Affected Categories footer specification, and the trigger → category mapping. Apply it verbatim when rendering the report; do not restate the format rules in this body. This detector emits the commands parameterization — all sections marked (commands only) in the pattern doc (## External Domain Events, ## Messaging Markers, the Summary rows for those two sections, the **Messaging:** per-method-block field) are emitted on this side. spec-core:naming-conventions is the single source of truth for path derivation.

Arguments

  • <domain_diagram> — path to the source domain Mermaid class diagram, at <dir>/<stem>.md. Used only for path derivation; the agent never reads its contents. The baseline for the diff is always git HEAD of the commands diagram, never the domain diagram.

Read the full file on GitHub · 259 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. 4d ago First seen · 259 lines · 0 tokens per session scan A 7652c7a76f8d

Subscribe to this mod's changes

commands-updates-detector is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 6,932 once invoked, about $0.0002 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.