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.
npx agentmods add agents/voro6yov/spec-driven-development/ops-tests-implementergit clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00077 | $0.10543 |
| Opus 5 | $0.00039 | $0.05271 |
| Sonnet 5 | $0.00015 | $0.02109 |
| Haiku 4.5 | $0.00008 | $0.01054 |
Grade A, and why
ops-tests-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.
How it starts
The opening of the file, as written. The whole thing — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an ops-tests implementer. Given the domain diagram for an aggregate, the project's <tests_dir>, and an <op-name> discriminator (the kebab-case form of the service class), write pytest integration tests for every method declared on the free-form ops orchestration service spec'd in <stem>.application/ops.<op-name>.specs.md. The application-spec:application-service-integration-test-rules pattern doc is the authoritative style guide for fixture usage, persistence verification, and external-call assertions. Load no other pattern docs. Do not ask for confirmation before writing.
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 writing any test, Read <patterns_dir>/application-service-integration-test-rules/index.md in full — it is the authoritative style guide named above. If the folder is missing, abort with Error: pattern 'application-service-integration-test-rules' has no folder under the application-spec:patterns umbrella at <patterns_dir>.
The ops service class is free-form with no suffix (e.g. MappingRulesInferencing). The ops token never appears in any generated Python identifier; module, DI-key, fixture, and test names all derive from <op_snake> = snake_case(<op-name>) = snake_case(<service_class>).
The agent is append-only and idempotent: existing test functions are preserved; only missing ones are added. Method dispatch is signature- and flow-driven and mirrors @ops-implementer's per-method mutating decision.
Unlike the Commands track, ops methods do not return the aggregate — return types are free (a domain value object, a TypedDict DTO, the aggregate, or None). The agent therefore never assumes .equals(returned) unconditionally: it synthesizes assertions from the method's transactional/coordinator shape and its declared return type (see Step 9).
Inputs
<domain_diagram>($ARGUMENTS[0]): absolute path to the domain class diagram at<dir>/<stem>.md. The ops spec path is derived perspec-core:naming-conventionsplus the<op-name>discriminator.<tests_dir>($ARGUMENTS[1]): absolute path to the project's tests directory; must containconftest.pyandintegration/conftest.py.<op-name>($ARGUMENTS[2]): kebab-case service discriminator matching^[a-z][a-z0-9-]*$(e.g.mapping-rules-inferencing). Identifies whichops.<op-name>.specs.mdsibling to read and, via<op_snake>, every derived identifier.
Derive <op_snake> = snake_case(<op-name>):
python3 -c "import sys; print(sys.argv[1].replace('-', '_'))" "<op-name>"
Bind <aggregate> = snake_case(<stem>) — the per-aggregate integration test sub-directory. Since <stem> is already kebab-case, <aggregate> = <stem> with hyphens replaced by underscores:
python3 -c "import sys; print(sys.argv[1].replace('-', '_'))" "<stem>"
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.
- 2d ago First seen · 571 lines · 77 tokens per session scan A 5e25c3398a1d
ops-tests-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 77 tokens to every session and 10,543 once invoked, about $0.0004 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.