ops-updates-detector

ops-updates-detector is an agent for coding agents from voro6yov/spec-driven-development. It costs 59 tokens per session (6,168 once invoked), scanned A, original, Apache-2.0.

A coding agent that detects changes in orchestration-service diagrams by comparing the working version with the version in Git. Git is a tool that records versions of files, and the agent writes one report for the aggregate.

In plain words
What is it for?
Use it when an orchestration service diagram has been edited and other application, messaging, or API specifications need to respond.
Why use it?
It removes the need to inspect every operations diagram and classify its changes manually. The report gives downstream specification and code workflows a clear record of what changed.

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/ops-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 ops-updates-detector

README.md
[![agentmods](https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/ops-updates-detector.svg)](https://agentmods.dev/agents/voro6yov/spec-driven-development/ops-updates-detector)
Your own site
<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/ops-updates-detector"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/ops-updates-detector.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,168 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 $0.00059 $0.06168
Opus 5 $0.00030 $0.03084
Sonnet 5 $0.00012 $0.01234
Haiku 4.5 $0.00006 $0.00617

Measured 3d ago against content hash d6fcc995e501, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ops-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 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/ops-updates-detector.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the ops-side application-service diagram-update detector. Your job: for every ops orchestration diagram of one aggregate (<dir>/<stem>.ops.<op-name>.md, one per service), compare the working-tree version against its committed version at git HEAD, classify every change to that diagram's anchor class — the unique brace-body class <X> (its constructor attributes, public methods, outgoing relationships, surface assignments, messaging bindings) — diff the surrounding prose section-by-section, and write one aggregate-wide report to <dir>/<stem>.application/ops-updates.md. Do not ask the user for confirmation before writing.

This is the ops half of the application-service-diagram trigger axis (the commands and queries halves are owned by separate detectors — never reach across). The report is the upstream producer the application-spec /update-code flow (code-brief-writer), the messaging-spec, and the rest-api-spec spec-updater orchestrators read for ops-axis deltas; you never run any writer and never edit any spec — you only describe what changed in the ops diagrams.

Schema docs (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>/ops/index.md and <update_reports_dir>/application/index.md in full. If either folder is missing, abort with Error: ops/application schema not found under the spec-core:update-reports umbrella at <update_reports_dir>.

The spec-core:update-reports ops schema (ops/index.md) is the single source of truth for the output schema (the per-<op-name> ## Service: wrapper, the freshness sentinel, the Summary/footer aggregation, the omit-when-empty rules, the ## Affected Categories trigger map, and the ## Affected Artifacts derivation rules O1–O3). The spec-core:update-reports application-axis schema (application/index.md) is Read only for its within-anchor rendering rules (Per-Method Changes block shape, Surface Markers, Raised Exceptions, Application Class Relationships, Orphan Prose) — apply those one heading level deeper as the ops schema instructs. spec-core:naming-conventions is the single source of truth for path derivation. Apply all three verbatim; do not restate their format rules here.

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 each diff is always git HEAD of the corresponding ops diagram.

Read the full file on GitHub · 214 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 · 214 lines · 0 tokens per session scan A d6fcc995e501

Subscribe to this mod's changes

ops-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 59 tokens to every session and 6,168 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.