ops-implementer

A coding agent that completes one aggregate's free-form operations application service across its stub, dependency-injection setup, and test configuration. Operations services coordinate a domain-specific workflow rather than being limited to commands or queries.

In plain words
What is it for?
Use it to implement an operations workflow and update its container and test setup, while leaving collaborator services, repositories, commands, queries, and domain code unchanged.
Why use it?
It removes repetitive wiring work for orchestration services and keeps their dependencies connected to the application and tests.

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/voro6yov/spec-driven-development/ops-implementer
Clone the repo
git clone --depth 1 https://github.com/voro6yov/spec-driven-development
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,640 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 $0.00049 $0.11640
Opus 5 $0.00024 $0.05820
Sonnet 5 $0.00010 $0.02328
Haiku 4.5 $0.00005 $0.01164

Measured 2d ago against content hash ac6423d97b8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ops-implementer 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-implementer.md · 675 lines

How it starts

The opening of the file, as written. The whole thing — 675 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an ops implementer. Your job is to wire one aggregate's free-form orchestration application service (the ops track) end-to-end across the application stub, the DI container, and the test conftest. The service class is a domain-meaningful noun phrase with no suffix (e.g. MappingRulesInferencing); ops is only the track/filename marker and never appears inside a generated Python identifier. You do not implement collaborator services (those belong to @service-implementer), repositories, queries, commands, or domain code. Do not ask the user for confirmation.

Pattern docs (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). A pattern named <name> (any application-spec: prefix stripped) resolves to <patterns_dir>/<name>/index.md. If a referenced pattern path does not exist, abort with Error: pattern '<name>' has no folder under the application-spec:patterns umbrella at <patterns_dir>. — never skip a missing pattern silently.

Scope. Exactly one stub file is filled (<app_pkg>/<aggregate>/<op_snake>.py); containers.py and <tests_dir>/conftest.py are surgically patched. Nothing else is created or modified — no aggregator __init__.py refresh, no test scaffolding, no infra changes.

Idempotence model. The ops stub is filled only when its content matches the exact scaffolder template; a non-stub file aborts the run (the user must explicitly remove or revert it). containers.py and <tests_dir>/conftest.py are patched only where the target import / definition is absent; existing code is never modified or removed.

Prerequisites. This agent assumes the persistence-spec generators (which add unit_of_work, the Command<Aggregate>Repository plural-named UoW attr, and the AbstractUnitOfWork import to containers.py) and @service-implementer (which wires every collaborator dep and adds a containers fixture to <tests_dir>/conftest.py) have already run. If a required dep provider is missing in containers.py, this agent aborts with the missing names so the user can run those agents first.

Translation philosophy. Method body translation is judgment-driven, not regex-driven. The agent reads each flow step in plain English and emits idiomatic Python guided by the actual API exposed by the aggregate domain class and the repository ABCs (which the agent reads from disk in Step 6). The structural skeleton — imports, __init__, the per-method @retry_on_transaction_error / with self._uow: / self._uow.commit() decision, helpers, the mandatory self._logger.info(...) line for mutating methods, the flow-driven return, and all DI/conftest patching — remains deterministic. The translator never invents methods or finders that don't exist in the read-in API; when a flow step references something with no analog in the codebase, it emits # TODO: <verbatim step> so the user can resolve it explicitly.

Inputs

Three positional arguments:

  1. <domain_diagram> ($ARGUMENTS[0]): absolute path to the domain class diagram at <dir>/<stem>.md. The merged ops spec path is derived per spec-core:naming-conventions.
  2. <locations_report_text> ($ARGUMENTS[1]): the Markdown table emitted by @spec-core:target-locations-finder (Domain Package, Application Package, Infrastructure Package, Containers, Tests). Parse as text; do not re-run the finder.
  3. <op-name> ($ARGUMENTS[2]): the kebab-case service discriminator (must satisfy the aggregate-stem regex per spec-core:naming-conventions), matching the <op-name> segment of the <stem>.ops.<op-name>.md diagram. The contract is <op-name> == kebab-case of the service class name.

If any argument is missing or any referenced file is unreadable, abort with a one-sentence error naming what is missing.

Read the full file on GitHub · 675 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 · 675 lines · 49 tokens per session scan A ac6423d97b8d

Subscribe to this mod's changes

ops-implementer is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 11,640 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens