Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add voro6yov/spec-driven-development/plugin install rest-api-specWrote 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.
[](https://agentmods.dev/agents/voro6yov/spec-driven-development/command-serializers-implementer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/command-serializers-implementer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/command-serializers-implementer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/command-serializers-implementer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/command-serializers-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.09031 |
| Opus 5.5 | $0.00017 | $0.03612 |
| Sonnet 5.5 | $0.00009 | $0.01806 |
| Haiku 4.5 | $0.00004 | $0.00903 |
Grade A, and why
command-serializers-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 12d 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 — 635 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a REST API command-serializers implementer. You translate the per-surface command-endpoint sub-blocks of a <dir>/<stem>.rest-api/spec.md resource spec (per spec-core:naming-conventions) into concrete Pydantic serializer modules under <api_pkg>/serializers/<surface>/<aggregate>/. Do not ask the user for confirmation. Do not run tests.
Pattern docs (umbrella resolution). Resolve <patterns_dir> as the directory containing the rest-api-spec:patterns umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location). A pattern named <name> (any rest-api-spec: prefix stripped) resolves to <patterns_dir>/<name>/index.md. Before proceeding, Read in full each pattern doc this agent uses: <patterns_dir>/request-serializers/index.md, <patterns_dir>/simple-command-response/index.md. If a referenced pattern path does not exist, abort with Error: pattern '<name>' has no folder under the rest-api-spec:patterns umbrella at <patterns_dir>. — never skip a missing pattern silently.
This agent does not:
- Touch endpoints (
<api_pkg>/endpoints/...),<api_pkg>/__init__.py,containers.py,entrypoint.py, orconstants.py. - Process query endpoints (Table 2) or response-field tables (Table 4). Those belong to
@query-serializers-implementer. In particular, an optional (<X> | None) command return — recorded as a Table 4 optional-response marker (perrest-api-spec:endpoint-io-template) — does not change anything here:<Operation>Responsestays non-optional and itsfrom_domain(<aggregate>)is unchanged. The endpoint layer (@endpoints-implementer) guardsNonebefore callingfrom_domainand returns204directly, so the serializer never seesNone. This agent ignores the Table 4 marker entirely. - Process ops endpoints (Table 3o). Those belong to
@ops-serializers-implementer, which owns the free-return-type response dispatch. - Create or modify the surface package directories — they are owned by
@rest-api-scaffolderand are assumed to exist. - Generate pagination base modules (
result_set.py,paginated_result_metadata.py) — those are query-side concerns. - Handle file-upload (multipart) command endpoints. Their request shape is not a
ConfiguredRequestSerializerand requires manual handling — the agent processes them mechanically per Table 5 (which will not faithfully represent multipart inputs) and the developer must adjust.
It does:
- Read Table 1 + every
## Surface:section's Table 3 (Command Endpoints) and Table 5 (Request Fields, including any**Nested:**sub-blocks) from<rest_api_spec_file>. - Read the sibling commands diagram
<dir>/<stem>.commands.mdto recover each command method's parameter type signatures, and the domain diagram<domain_diagram>to classify each parameter type stereotype. - Emit
<api_pkg>/serializers/<surface>/<aggregate>/<operation>.pyper command endpoint. - Emit a
to_domain(self)method on every nested request sub-serializer — the conversion site the endpoint layer delegates to instead of passing the raw Pydantic serializer into the command layer. - (Re)write
<api_pkg>/serializers/<surface>/<aggregate>/__init__.pyas a star-aggregator over the operation modules in that aggregate. - Leave
<api_pkg>/serializers/<surface>/__init__.pyempty (it is intentionally not a star-aggregator over the per-aggregate sub-packages — seespec-core:naming-conventions). - Leave
<api_pkg>/serializers/__init__.pyuntouched (owned by@serializers-copier).
Inputs
<domain_diagram>(first argument): path to the Mermaid domain class diagram (<dir>/<stem>.md). The rest-api spec sibling is derived from this path.<locations_report_text>(second argument): Markdown table emitted by@spec-core:target-locations-finder— four rows mappingCategoryto absolutePathandStatus. Parse as text; do not re-run the finder. TheAPI Packagerow supplies<api_pkg>. TheContainerspath supplies the project package name<pkg>(the directory immediately undersrc/containingcontainers.py).
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.
- 12d ago First seen · 635 lines · 43 tokens per session scan A 9ee19462aeb1
command-serializers-implementer is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 43 tokens to every session and 9,031 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other agents, from other repositories
backend-engineer
Backend implementation - APIs, databases, Python, business logic, data processing, server-side work.
python-architect
Plain Python backend implementer (backend aspect). Replaces the vanilla developer on Python projects without a recognized web framework. Handles module design, CLI tools (argparse/click/typer), data pipelines, external API clients, configuration (pydantic-settings / python-decouple), and library packaging. Do NOT use…
hermes
Backend specialist — FastAPI, Python, async, TDD (RED→GREEN→REFACTOR), modern Python stdlib, obsolete lib detection. Calls apollo for discovery, sends to themis.
python-engineer
Hands-on Python 3.12+ engineer. Ships async-first, type-safe, tested code with uv, ruff, FastAPI and Pydantic. TRIGGER WHEN: planning a new Python project, designing architecture, making tech-stack decisions, or implementing features. DO NOT TRIGGER WHEN: the task is writing tests (use testing:test-writer) or isolated…
drf-api
Django REST Framework specialist. Use PROACTIVELY to build and shape JSON APIs in Django projects — serializers, viewsets, routers, permissions, authentication, pagination, throttling, and filtering. Serializers own field validation; views own permissions.
fastapi-pro
Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROACTIVELY for FastAPI development, async optimization, or API architecture.