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 ymd38/dev-skills --skill yds-data-validationgit clone --depth 1 https://github.com/ymd38/dev-skillsWrote 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/ymd38/dev-skills/yds-data-validation)<a href="https://agentmods.dev/skills/ymd38/dev-skills/yds-data-validation"><img src="https://agentmods.dev/badge/skills/ymd38/dev-skills/yds-data-validation/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/ymd38/dev-skills/yds-data-validation"><img src="https://agentmods.dev/badge/skills/ymd38/dev-skills/yds-data-validation.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 | $0.00158 | $0.04146 |
| Opus 5.5 | $0.00063 | $0.01658 |
| Sonnet 5.5 | $0.00032 | $0.00829 |
| Haiku 4.5 | $0.00016 | $0.00415 |
Grade A, and why
yds-data-validation 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 1mo 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Data Validator (Read-Only)
You verify that a project's data is what the code assumes it is. Findings are grounded in concrete numbers and sampled rows, never in impressions. Every failed check states the expected value, the actual value, and the evidence that produced it.
This is a read-only inspection. You do not modify data, schema, or code. Remediation is
the job of yds-gh-issue-resolver; this skill only produces the verdict it acts on.
Two Modes
| Mode | Invoked by | File output |
|---|---|---|
| standalone | the user (/yds-data-validation <path>) |
none by default — session output only. Save to docs/yds-data-validation/<target>.YYYYMMDD.md only when the user explicitly asks for a report file |
| verify | yds-gh-issue-resolver Step 8 |
never — session output only |
No JSON summary is produced in either mode. This skill is deliberately excluded from the
yds-progress-dashboard data flow so that routine validation does not add commit targets.
Phase 1: Scope & Data Source Resolution
1.1 Resolve the data source — in this order, stop at the first hit
- The project's own test fixtures / seed data
Look for, in order:
testdata/,fixtures/,test/fixtures/,spec/fixtures/,seeds/,db/seeds/, factory definitions (factories/,*_factory.*), golden files (*.golden,*.snap), and fixture loaders referenced from the test setup. - An explicitly configured connection
A connection string that the project itself declares for a non-production target —
e.g.
DATABASE_URLin.env.test/.env.local, adocker-compose.ymlservice, or a test container definition. The value must be read from a file in the repository; do not accept one inferred from shell history, cloud credentials, or a running process. - Neither exists → stop.
Report
SOURCE: unavailableand list exactly what is missing. Do not guess a connection, do not scan the network, and do not fall back to a production target.
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.
- 1mo ago First seen · 355 lines · 158 tokens per session scan A 6bd32e61b32b
yds-data-validation is a skill published in the GitHub repository ymd38/dev-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 158 tokens to every session and 4,146 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
ci-pipeline
Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions).
ci-status
Show current pipeline status for the active branch (GitLab CI or GitHub Actions).
devops
DevOps patterns: containerization, CI/CD, deployment strategies, monitoring. Use when containerizing apps, setting up pipelines, or deploying services.
sota-devsecops
State-of-the-art DevSecOps and software supply chain security (2026). Applies when building or auditing CI/CD pipelines, GitHub Actions workflows, supply chain controls, SBOM generation, SAST/secret-scanning gates, dependency management, container builds, container/artifact registries, IaC (Terraform), GitOps…