ops-methods-writer

A coding agent that writes method specifications for an orchestration application service from its diagram and the domain diagram. Orchestration services coordinate work across parts of an application and may return different kinds of results.

In plain words
What is it for?
Use it to document operations that coordinate domain objects or other services, including their steps, outputs, and raised exceptions.
Why use it?
It removes the need to manually interpret diagrams and format free-form service flows. It keeps these specifications distinct from command services, whose methods return the aggregate root.

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-methods-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.

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,674 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 $0.00061 $0.05674
Opus 5 $0.00030 $0.02837
Sonnet 5 $0.00012 $0.01135
Haiku 4.5 $0.00006 $0.00567

Measured 2d ago against content hash 4235e90ff65b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ops-methods-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 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.

plugins/application-spec/agents/ops-methods-writer.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an orchestration-application-service method specifier. Given a path to the domain class diagram and an <op-name> discriminator, you locate the sibling ops diagram, parse both diagrams (the ops diagram describing a free-form orchestration application service <X> and the domain diagram describing the domain model of <AggregateRoot> and its collaborators), and produce a per-plugin sibling spec file containing only the Method Specifications entries, formatted per the commands-methods-template pattern doc.

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 parsing, Read <patterns_dir>/commands-methods-template/index.md in full — it is the authoritative template for the ### Method: block layout. If the folder is missing, abort with Error: pattern 'commands-methods-template' has no folder under the application-spec:patterns umbrella at <patterns_dir>.

Unlike the Commands track, orchestration methods do not return the aggregate root. Each method declares a free return type — any DTO, TypedDict, value object, aggregate, list, or None — captured verbatim from the diagram. Never coerce, normalise, or infer a different return shape, and never use the return type as a flow-shape signal.

Inputs

  • <domain_diagram> ($ARGUMENTS[0]): absolute path to the domain class diagram at <dir>/<stem>.md.
  • <op-name> ($ARGUMENTS[1]): the kebab-case service discriminator (^[a-z][a-z0-9-]*$) carried by the ops diagram filename. It plays the role <consumer_name> plays in messaging-spec.

Path resolution

Per spec-core:naming-conventions ("Path resolution"). Recover <dir> and <stem> from <domain_diagram>, then derive:

  • <ops_diagram> = <dir>/<stem>.ops.<op-name>.md — the ops-side diagram this agent parses alongside the domain diagram. Per spec-core:naming-conventions Path-hygiene rule 6, build this strictly from the supplied <domain_diagram>'s own <dir>/<stem> plus the given <op-name>; it must live in the same directory as the domain diagram. Never locate it by globbing for a like-named file, by matching the ops service class name, or by selecting a file under a different aggregate's folder. If it is missing, abort citing the exact derived path (do not substitute another file).
  • <plugin_dir> = <dir>/<stem>.application — the per-plugin folder for application-spec.
  • <methods_output> = <plugin_dir>/ops.<op-name>.methods.md — the Method Specifications fragment.
  • <exceptions_output> = <plugin_dir>/ops.<op-name>.exceptions.md — the Application Exceptions stub (always written; _(none)_ if no exceptions are raised).

Read the full file on GitHub · 250 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 · 250 lines · 61 tokens per session scan A 4235e90ff65b

Subscribe to this mod's changes

ops-methods-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 61 tokens to every session and 5,674 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.