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 rjroy/vibe-garden/plugin install lore-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/rjroy/vibe-garden/define-validation)<a href="https://agentmods.dev/skills/rjroy/vibe-garden/define-validation"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/define-validation.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00311 |
| Opus 5 | $0.00020 | $0.00156 |
| Sonnet 5 | $0.00008 | $0.00062 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
define-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 6d 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.
What it actually says
Define Validation
Validation answers: "How will the AI know this is done?"
It must be behavioral and actionable — something the AI can actually run or observe. "Run the CLI with these args and confirm the output contains X." "Use Playwright to confirm clicking the button triggers Y." "Run the test suite and check it passes." Not "verify the UX feels right."
Add a validation section to an existing spec or plan. If none exists, save standalone to .lore/work/validation/[topic].md. Load ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md for the frontmatter fields before writing.
When saving standalone, write the body in Markdown per the "Body Format" section of ${CLAUDE_PLUGIN_ROOT}/shared/frontmatter-schema.md. Reach for embedded inline HTML only when a visual carries meaning prose can't, such as a diagram separating automated from manual steps.
What counts
- Unit or integration tests
- CLI invocations with expected output
- Browser automation steps
- Manual steps the AI can follow and report on
- Lint and type checks when behavior depends on them
Structural assertions ("verify this function appears only once") don't count. If a regression must not recur, write a test that fails when the behavior regresses, not when lines move.
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.
- 6d ago First seen · 25 lines · 41 tokens per session scan A 19310af4e8bb
define-validation is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 311 once invoked, about $0.0002 per session on Opus 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
deep-project
Decomposes vague, high-level project requirements into well-scoped planning units for /deep-plan. Use when starting a new project that needs to be broken into manageable pieces.
bottle
Bootstrap a new or existing project with a small, file-based documentation system so Claude Code keeps context, lessons, and decisions across session restarts instead of starting cold every time. Sets up a handful of markdown files under .claude/ (standing rules, a free-form note to your next session, a phased…
init-rpm
Project setup and verification. First run creates rpm context for a project. Repeat runs verify that an existing rpm setup matches the latest expected layout and apply safe migrations.
backlog
Manage the rpm backlog (long-term project tasks in docs/rpm/future/tasks.org — distinct from Claude's native TaskCreate list, which is session-scoped). Add, list, review, postpone, or complete entries. TRIGGER on natural-language backlog operations — phrasings like "backlog X", "add X to backlog", "add to backlog"…
pace-change
Use when user says "不做了", "搁置", "停掉", "加一个", "加需求", "追加", "改需求", "需求变了", "范围变了", "优先级调", "延后", "提前", "砍掉", "先做这个", "排到前面", "恢复", "捡回来", "pace-change", or wants to add, pause, resume, reprioritize, modify, undo, batch change, or query change history. NOT for code implementation (/pace-dev) or project init (/pace-init).
pace-release
Use when user says "发布", "部署", "上线", "release", "pace-release", or wants to create, deploy, or close a release. NOT for CI/CD pipeline management (use /pace-sync). NOT for code implementation (use /pace-dev).