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 init-persistencegit 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/init-persistence)<a href="https://agentmods.dev/skills/voro6yov/spec-driven-development/init-persistence"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/init-persistence/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/init-persistence"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/init-persistence.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 | $0.00020 | $0.01589 |
| Opus 5.5 | $0.00008 | $0.00636 |
| Sonnet 5.5 | $0.00004 | $0.00318 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
init-persistence 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the project-wide persistence initializer. Ensure that the current repository has the minimum directory structure required for any subsequent @persistence-spec:code-generator (or /persistence-spec:generate-persistence) run:
- the
infrastructure/,infrastructure/repositories/, andinfrastructure/repositories/tables/Python packages, - the
infrastructure/unit_of_work/andinfrastructure/query_context/packages copied from thespec-core:modulesumbrella (withcontainers.pyproviders wired), - the
extras/database_session/package copied from thespec-core:modulesumbrella and re-exported throughextras/__init__.py, etc/migrator/migrations/with a minimal Liquibasemaster.yamlstub,tests/andtests/integration/test packages with emptyconftest.pyfiles (plus thequery_contextintegration fixture).
This skill performs no aggregate-specific work — per-aggregate sub-packages, tables, mappers, migrations, and repositories are still owned by the per-aggregate scaffolders.
Inputs
None. The skill operates entirely on the current working directory.
Output discipline
This skill is silent on success. Print nothing — not even a closing confirmation — when every step succeeds, whether the work happened, was partial, or was already done. Print only on failure: a single ERROR: ... line naming the failure, then stop. Do not summarize, do not emit progress text, do not echo sub-agent confirmation lines.
Workflow
Step 1 — Discover src/ and the project package
Invoke @spec-core:project-package-finder with prompt /init-persistence. Wait for completion. If it returns a line beginning ERROR:, surface that line verbatim and stop.
Otherwise parse its report table and bind <repo> = the Repo value, <src> = the Src value, and <pkg> = the Package value.
Bind:
<pkg_dir>=<src>/<pkg><containers_file>=<pkg_dir>/containers.py<tests_dir>=<src>/tests<infra_dir>=<pkg_dir>/infrastructure<repos_dir>=<infra_dir>/repositories<tables_dir>=<repos_dir>/tables<migrations_dir>=<repo>/etc/migrator/migrations<master_yaml>=<migrations_dir>/master.yaml
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 · 141 lines · 0 tokens per session scan A 320c25eb2559
init-persistence is a skill published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,589 once invoked, about $0.0001 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
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
azure-cosmos-db-py
Build Azure Cosmos DB NoSQL services with Python/FastAPI following production-grade patterns. Use when implementing database client setup with dual auth (DefaultAzureCredential + emulator), service layer classes with CRUD operations, partition key strategies, parameterized queries, or TDD patterns for Cosmos. Triggers…
Drizzle ORM Testing
Testing patterns for Drizzle ORM covering migration testing, query builder testing, transaction testing, and database integration testing with PostgreSQL, SQLite, and MySQL.
finance-weekly-outlook
Generate a source-backed weekly financial trading outlook from daily-finance, finance-core-analysis, and finance-explosive-article outputs plus fresh authoritative market data. Use when the user asks for future-one-week market outlook, weekly bullish/bearish sectors, stock picks, China A-share and US stock coverage…