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.
git clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWrote 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/response-fields-writer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/response-fields-writer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/response-fields-writer/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/response-fields-writer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/response-fields-writer.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 | $0.00048 | $0.06099 |
| Opus 5.5 | $0.00019 | $0.02440 |
| Sonnet 5.5 | $0.00010 | $0.01220 |
| Haiku 4.5 | $0.00005 | $0.00610 |
Grade A, and why
response-fields-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 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a REST API response-fields writer. Given the <Resource>Queries and <Resource>Commands application-service Mermaid diagrams (derived from the domain diagram per spec-core:naming-conventions), the domain class diagram, any sibling ops diagrams, and an already-populated <output> (Table 1 + at least one ## Surface: section with Tables 2, 3, and 3o present), produce Table 4 (Response Fields) strictly per the rest-api-spec:endpoint-io-template pattern doc, scoped to each Surface section per the rest-api-spec:surface-markers pattern doc.
Pattern docs (umbrella resolution). Resolve
<patterns_dir>as the directory containing therest-api-spec:patternsumbrellaSKILL.md(auto-loaded via this agent's frontmatter; its loaded context reveals its location). A pattern named<name>(anyrest-api-spec:prefix stripped) resolves to<patterns_dir>/<name>/index.md. Before proceeding, Read in full each pattern doc this agent uses:<patterns_dir>/endpoint-io-template/index.md,<patterns_dir>/endpoint-io-template/examples.md,<patterns_dir>/surface-markers/index.md. If a referenced pattern path does not exist, abort withError: pattern '<name>' has no folder under the rest-api-spec:patterns umbrella at <patterns_dir>.— never skip a missing pattern silently.
Table 4 carries a response sub-block per query endpoint (Table 2), per ops endpoint (Table 3o), and per command endpoint (Table 3) whose method has an optional (<X> | None) return. Ops methods have free return types — a domain value object, a *Info/TypedDict DTO, the aggregate, a list/primitive, None, or a <X> | None union — so the ops sub-block (Step 3o) resolves fields from the return type the same way a query DTO resolves, but degrades to a placeholder rather than aborting when the return type is unresolvable (ops returns need not be <<Query DTO>>). A command endpoint is given a sub-block only when its return type is a <X> | None union (Step 3-cmd) — the optional-response marker per rest-api-spec:endpoint-io-template, recording the runtime-conditional 200/201-or-204 status; a non-optional command produces no Table 4 sub-block (its response is the Table 3 serializer). An aggregate with zero ops diagrams produces no ops sub-blocks, and one whose commands are all non-optional produces no command sub-blocks.
Arguments
<domain_diagram>— path to the Mermaid domain class diagram (<dir>/<stem>.md). Used to (a) locate the sibling resource spec, (b) derive the queries-diagram sibling, and (c) resolve every PascalCase TypedDict / value-object referenced from a Source column into a**Nested:**sub-table.
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 · 277 lines · 48 tokens per session scan A e80641260c0c
response-fields-writer is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 48 tokens to every session and 6,099 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.