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 skills add voro6yov/spec-driven-development --skill new-servicegit 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/skills/voro6yov/spec-driven-development/new-service)<a href="https://agentmods.dev/skills/voro6yov/spec-driven-development/new-service"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/new-service/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/skills/voro6yov/spec-driven-development/new-service"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/new-service.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 | $0.00109 | $0.01928 |
| Opus 5.5 | $0.00044 | $0.00771 |
| Sonnet 5.5 | $0.00022 | $0.00386 |
| Haiku 4.5 | $0.00011 | $0.00193 |
Grade A, and why
new-service 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You scaffold a new service repository. The tree is rendered by scaffold.py — a deterministic, stdlib-only script that ships next to this file — never by hand. Your job is to collect the inputs, run the script, initialize the spec layers, verify, commit, and report. Do not write or edit any generated file yourself.
Inputs
$ARGUMENTS is <service-name> followed by optional flags, passed through to the script verbatim:
| Argument | Meaning | Default |
|---|---|---|
<service-name> |
kebab-case name; the new directory and the uv project name | — (required) |
--package PKG |
importable package under src/ |
snake_case of the name |
--python X.Y |
CPython minor version (3.11+) | 3.12 |
--port N |
HTTP port of the API process | 8000 |
--no-persistence |
omit Postgres/SQLAlchemy, Datasources, the Liquibase migrator |
layer on |
--no-rest |
omit FastAPI, the api/ package, create_fastapi/run_api, the serve command |
layer on |
--no-messaging |
omit RabbitMQ, the vendored pubsub, the Messaging/MessageBrokers containers |
layer on |
--dry-run |
print the planned tree; write nothing | off |
The service is created in the current working directory as ./<service-name>. The script refuses if that path exists — it never overwrites.
If $ARGUMENTS is empty, use AskUserQuestion once to collect the service name and which layers to include, then continue. Never ask when a name was given — the flags have defaults.
Workflow
Step 1 — Resolve the two directories
<skill_dir>— the directory containing thisSKILL.md(shown when the skill loads). The script is<skill_dir>/scaffold.py.<modules_dir>— invoke thespec-core:modulesskill via theSkilltool and take the directory containing itsSKILL.md. If spec-core is not installed, stop withERROR: the spec-core plugin is required (spec-core:modules supplies the vendored runtime modules).
Step 2 — Render
python3 "<skill_dir>/scaffold.py" $ARGUMENTS --modules-dir "<modules_dir>"
What ships with it
31 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scaffold.py 11 KB runs code
- templates/docker-compose.yml 2.0 KB
- templates/dockerignore 71 B
- templates/docs/README.md 1.2 KB
- templates/empty 0 B
- templates/env.example 714 B
- templates/etc/migrator/Dockerfile 220 B
- templates/etc/migrator/entrypoint.sh 833 B runs code
- templates/etc/migrator/migrations/master.yaml 79 B
- templates/etc/service/Dockerfile 895 B
- templates/gitignore 107 B
- templates/Makefile 1.7 KB
- templates/pyproject.toml 3.7 KB
- templates/python-version 13 B
- templates/README.md 2.0 KB
- templates/src/pkg/__init__.py 27 B runs code
- templates/src/pkg/__main__.py 289 B runs code
- templates/src/pkg/api/__init__.py 103 B runs code
- templates/src/pkg/api/endpoints/__init__.py 109 B runs code
- templates/src/pkg/api/endpoints/healthcheck.py 811 B runs code
- templates/src/pkg/api/endpoints/service_info.py 429 B runs code
- templates/src/pkg/api/fastapi_auth.py 996 B runs code
- templates/src/pkg/application/retry_transaction.py 1.5 KB runs code
- templates/src/pkg/constants.py 214 B runs code
- templates/src/pkg/containers.py 3.4 KB runs code
- templates/src/pkg/entrypoint.py 2.4 KB runs code
- templates/src/pkg/extras/__init__.py 95 B runs code
- templates/src/pkg/infrastructure/access_management.py 366 B runs code
- templates/src/pkg/settings.py 1.2 KB runs code
- templates/src/tests/conftest.py 355 B runs code
- templates/src/tests/unit/test_smoke.py 1.3 KB runs code
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 · 113 lines · 109 tokens per session scan A 8927c9a2a074
new-service is a skill published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,928 once invoked, about $0.0004 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 skills, from other repositories
azure-containerregistry-py
Manage container images, artifacts, and repositories in Azure Container Registry.
airflow
Apache Airflow is a platform for programmatically authoring, scheduling, and monitoring workflows. Learn to write DAGs, use operators, set up connections, configure scheduling, and deploy with Docker Compose.
python-install-skill
An installation helper for Python 3, a programming language and runtime. It checks whether Python is already installed and supports package-manager or Docker-based installation on common operating systems.
docker_packaging
A set of rules and templates for packaging a Python MCP service in Docker. Docker packages an application and its dependencies into a repeatable container that can run on another machine.
python-containers
Python container optimization — slim images (not Alpine), virtualenv, multi-stage, pip/poetry/uv, musl gotchas (1GB to 120MB). Use when working with Python containers or optimizing image sizes.
code-style
A set of coding and repository conventions covering Python, Telegram bots, project structure, typing, logging, documentation, Docker, and deployment files.