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 spec-coreWrote 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/modules)<a href="https://agentmods.dev/skills/voro6yov/spec-driven-development/modules"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/modules/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/modules"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/modules.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 | $0.00070 | $0.01565 |
| Opus 5.5 | $0.00028 | $0.00626 |
| Sonnet 5.5 | $0.00014 | $0.00313 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade B, and why
modules scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
They are homed here in spec-core — the shared foundation every spec plugin already depends on — so there is **one** canonical source with **one** resolvable path, instead of each plugin resolving its own bundle via britt How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference modules (spec-core)
The spec pipeline ships a set of runtime contract modules — real Python source the generated code imports (Entity, ValueObject, guards, UnitOfWork, QueryContext, DatabaseSession, the serializer base). They are not generated per-aggregate; they are copied verbatim into the target repo once, by each layer's init/scaffold flow.
They are homed here in spec-core — the shared foundation every spec plugin already depends on — so there is one canonical source with one resolvable path, instead of each plugin resolving its own bundle via brittle find ~/.claude/plugins globs or impossible "walk up to a plugins/ ancestor" heuristics. Those heuristics do not work from an agent's or skill's runtime Bash (the ${CLAUDE_PLUGIN_ROOT} variable is not exposed there); the umbrella mechanism does, because loading this skill reveals its own directory.
Each group is a supporting folder of real .py files (not an index.md doc) sibling to this SKILL.md. The files are never auto-loaded into context — consumers copy them to disk on demand.
Resolution rule
A consumer resolves <modules_dir> as the directory containing this SKILL.md — its loaded context (frontmatter auto-load for agents, or the Skill tool for skills) reveals its location. A group named <group> is then the folder <modules_dir>/<group>/.
Copy a group with a directory-tree copy from the resolved absolute path:
cp -r <modules_dir>/<group> <destination>
Be idempotent: never overwrite a file that already exists at the destination; copy only what is missing. Preserve contents byte-for-byte. A group name with no matching folder is an error — report it loudly; never skip it silently.
Catalog
| Group | Folder | Copied by | Contents |
|---|---|---|---|
| shared | shared/ | domain-spec:init-domain |
domain primitives — entity.py, value_object.py, entity_id.py, event.py, command.py, clock.py, extended_enum.py, exceptions.py, pagination/result-set DTOs, and the nested guards/ package |
| database_session | database_session/ | persistence-spec:database-session-scaffolder |
__init__.py, constants.py, database_session.py |
| unit_of_work | unit_of_work/ | persistence-spec:context-package-scaffolder (unit_of_work axis) |
__init__.py, abstract_unit_of_work.py, sql_alchemy_unit_of_work.py |
| query_context | query_context/ | persistence-spec:context-package-scaffolder (query_context axis) |
__init__.py, abstract_query_context.py, sql_alchemy_query_context.py |
| serializers | serializers/ | rest-api-spec:serializers-copier |
error.py, configured_base_serializer.py, json_utils.py |
| pubsub | pubsub/ | project-scaffold:new-service (messaging layer), messaging-spec:init-messaging |
vendored deps_pubsub core (commands/, events/, messaging/, common/) plus the RabbitMQ driver as the rabbitmq/ sub-package; installed at <pkg>/extras/pubsub |
| observability | observability/ | project-scaffold:new-service |
vendored deps_observability_instrumentation — setup_instrumentation, instrument_fast_api, instrument_messaging, instrument_external_clients, OTLP exporters only; installed at <pkg>/extras/observability |
What ships with it
60 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.
- database_session/__init__.py 113 B runs code
- database_session/constants.py 246 B runs code
- database_session/database_session.py 2.4 KB runs code
- observability/__init__.py 207 B runs code
- observability/constants.py 60 B runs code
- observability/exporters/__init__.py 153 B runs code
- observability/exporters/exporter_type.py 96 B runs code
- observability/exporters/ifactory.py 350 B runs code
- observability/exporters/otlp_exporter/__init__.py 50 B runs code
- observability/exporters/otlp_exporter/factory.py 777 B runs code
- observability/exporters/otlp_exporter/settings.py 413 B runs code
- observability/external_clients/__init__.py 66 B runs code
- observability/external_clients/external_client_tracing.py 1.3 KB runs code
- observability/external_clients/external_storage_tracing.py 836 B runs code
- observability/external_clients/instrumentation.py 1.1 KB runs code
- observability/external_clients/interfaces.py 537 B runs code
- observability/extras/deps_settings/__init__.py 104 B runs code
- observability/extras/deps_settings/base_settings.py 8.5 KB runs code
- observability/extras/deps_settings/exceptions.py 1.0 KB runs code
- observability/extras/deps_settings/validators.py 3.7 KB runs code
- observability/fast_api/__init__.py 66 B runs code
- observability/fast_api/i_can_add_middleware.py 311 B runs code
- observability/fast_api/instrumentation.py 244 B runs code
- observability/fast_api/tracing_middleware.py 1.3 KB runs code
- observability/pubsub/__init__.py 66 B runs code
- observability/pubsub/instrumentation.py 483 B runs code
- observability/pubsub/interfaces.py 632 B runs code
- observability/pubsub/message_consumer_tracing.py 2.6 KB runs code
- observability/pubsub/message_producer_tracing.py 1.7 KB runs code
- observability/settings.py 313 B runs code
- observability/setup_telemetry.py 1.5 KB runs code
- pubsub/__init__.py 444 B runs code
- pubsub/commands/__init__.py 0 B runs code
- pubsub/commands/common/__init__.py 339 B runs code
- pubsub/commands/common/command_message_headers.py 793 B runs code
- pubsub/commands/common/command_reply_outcome.py 105 B runs code
- pubsub/commands/common/command_util.py 710 B runs code
- pubsub/commands/common/command.py 132 B runs code
- pubsub/commands/common/failure.py 132 B runs code
- pubsub/commands/common/outcome.py 68 B runs code
- pubsub/commands/common/reply_message_headers.py 138 B runs code
- pubsub/commands/common/success.py 132 B runs code
- pubsub/commands/consumer/__init__.py 362 B runs code
- pubsub/commands/consumer/command_dispatcher.py 3.4 KB runs code
- pubsub/commands/consumer/command_handler_params.py 1.2 KB runs code
- pubsub/commands/consumer/command_handler_reply_builder.py 964 B runs code
- pubsub/commands/consumer/command_handler.py 1011 B runs code
- pubsub/commands/consumer/command_handlers_builder.py 1012 B runs code
- pubsub/commands/consumer/command_handlers.py 780 B runs code
- pubsub/commands/consumer/command_message.py 804 B runs code
- pubsub/commands/consumer/command_with_destination_builder.py 940 B runs code
- pubsub/commands/consumer/command_with_destination.py 659 B runs code
- pubsub/commands/producer/__init__.py 46 B runs code
- pubsub/commands/producer/command_producer.py 1.1 KB runs code
- pubsub/common/__init__.py 0 B runs code
- pubsub/common/deps_settings/__init__.py 104 B runs code
- pubsub/common/deps_settings/base_settings.py 8.5 KB runs code
- pubsub/common/deps_settings/exceptions.py 1.0 KB runs code
- pubsub/common/deps_settings/validators.py 3.7 KB runs code
- pubsub/drivers.py 135 B 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 · 57 lines · 70 tokens per session scan B 52e91f045493
modules is a skill published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,565 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…