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 generate-messaginggit 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/generate-messaging)<a href="https://agentmods.dev/skills/voro6yov/spec-driven-development/generate-messaging"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/generate-messaging/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/generate-messaging"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/generate-messaging.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 | $0.00054 | $0.00768 |
| Opus 5.5 | $0.00022 | $0.00307 |
| Sonnet 5.5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
generate-messaging 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 14d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a messaging end-to-end orchestrator. Generate the messaging consumer spec and the messaging code for the consumer named $ARGUMENTS[1] (<consumer_name>), scoped to the aggregate whose domain diagram is $ARGUMENTS[0], by chaining two orchestrator agents sequentially. Each agent runs the heavy fan-out in its own isolated context and returns only a one-line report — this umbrella stays lean.
This is a TWO-PHASE skill
This skill is not complete until both phases finish:
- Phase 1 —
messaging-spec:specs-generatoragent (writes<stem>.messaging/<consumer_name>.mdwith Tables 1, 2, and 3) - Phase 2 —
messaging-spec:code-generatoragent (scaffolds the per-consumer messaging submodule, implements external events, handlers, and the dispatcher factory, wires the dispatcher into containers/entrypoint/main, prepares test fixtures, and writes handler integration tests)
Phase 1 ends with its own confirmation line such as Messaging spec generation complete for .... That message refers to Phase 1 only. It is not the end of this skill — you MUST continue to Phase 2 immediately. The single most common failure mode of this skill is stopping after Phase 1; do not do that.
Inputs
$ARGUMENTS[0]— the path to the aggregate's Mermaid domain class diagram (<dir>/<stem>.md).$ARGUMENTS[1]— the kebab-case consumer name (matching^[a-z][a-z0-9-]*$), as it appears in the%% Messaging - <consumer_name>marker inside the commands diagram.
All artifacts produced by Phase 1 land in <dir>/<stem>.messaging/<consumer_name>.md per spec-core:naming-conventions; Phase 2 reads from there. The sibling commands diagram (<commands_diagram>) is derived internally by each spawned agent; this umbrella only forwards the domain diagram path and the consumer name.
Workflow
Spawn each agent in its own message (via the Agent tool) and wait for it to complete before spawning the next. Do not collapse them into a single message.
Step 1 of 2 — Generate the messaging consumer spec
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.
- 14d ago First seen · 47 lines · 0 tokens per session scan A 627b130cadca
generate-messaging is a skill published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 14d ago), licensed Apache-2.0. It adds 54 tokens to every session and 768 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
enterprise-integration-testing
Use when testing enterprise integrations across SAP, middleware, WMS, or backend systems, validating E2E enterprise flows, testing SAP-specific patterns (RFC, BAPI, IDoc, OData, Fiori), or enforcing cross-system quality gates.
backend/testing-guide
A guide for writing backend tests: small unit tests, tests that check connected parts such as an API and database, and end-to-end tests that follow a complete user flow.
endpoint-probe
Probes each major Agent Monitor API route — /api/stats, /api/analytics, /api/sessions, /api/pricing/cost, /api/workflows/runs, /api/cc-config/overview — and reports each one's HTTP status, latency, and response shape, flagging which are reachable. Use to verify a dashboard install is wired up correctly.
emulate-seed
Generate emulate seed configs for stateful API emulation. Wraps Vercel's emulate tool for GitHub, Vercel, Google OAuth, Slack, Apple Auth, Microsoft Entra, AWS, Okta, Clerk, Resend, Stripe, and MongoDB Atlas APIs — full state machines, not mocks. Use when setting up test environments, CI pipelines, integration tests…
selenide-skill
Generates Selenide tests in Java. Concise UI testing framework built on Selenium with automatic waits and fluent API. Use when user mentions "Selenide", "$(selector)", "shouldBe(visible)", "Selenide Java". Triggers on: "Selenide", "$() selector", "shouldBe", "shouldHave", "Selenide test".