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 agentmods add skills/clubpay/ronykit/verification-before-completionnpx skills add clubpay/ronykit --skill verification-before-completiongit clone --depth 1 https://github.com/clubpay/ronykitWrote 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/clubpay/ronykit/verification-before-completion)<a href="https://agentmods.dev/skills/clubpay/ronykit/verification-before-completion"><img src="https://agentmods.dev/badge/skills/clubpay/ronykit/verification-before-completion.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 | $0.00048 | $0.00554 |
| Opus 5 | $0.00024 | $0.00277 |
| Sonnet 5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
verification-before-completion 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Before Completion
Claiming work is complete without verifying it is guesswork, not efficiency. Evidence before claims, always.
The rule
No completion claim without fresh verification evidence.
If you have not run the verifying command for the change in front of you, you cannot say it passes, builds, or is fixed.
The gate (run before any "done")
- Identify the command that proves the claim.
- Run the full command fresh — not a partial or cached run.
- Read the full output: exit code, failure count, warnings.
- Verify the output actually confirms the claim.
- Then state the result, with the evidence.
What each claim actually requires
| Claim | Sufficient evidence | Not enough |
|---|---|---|
| Tests pass | Test output: 0 failures | "should pass", a previous run |
| Linter clean | Linter output: 0 errors | a partial check |
| Build succeeds | Build exits 0 | linter passing, "logs look fine" |
| Bug fixed | The original symptom no longer reproduces | code changed, assumed fixed |
| Regression test works | Red→green verified (fails without the fix) | test passes once |
| Requirements met | Line-by-line check against the spec | "tests pass, so we're done" |
| Delegated work done | Diff/output inspected directly | the agent reported success |
Red flags — stop and verify
- Words like "should", "probably", "seems to", or celebrating before running anything ("Done!", "Perfect!").
- About to commit, push, or open a PR without a fresh run.
- Trusting a subagent's "success" without checking the diff.
- "Just this once" / "I'm confident" / "the linter passed so it compiles".
Regression tests: prove red→green
A regression test that only passes proves nothing. Confirm it fails without the fix:
write test → run (fails) → apply fix → run (passes)
Bottom line
Run the command. Read the output. Then make the claim. No shortcuts.
Adapted from the verification-before-completion skill in
obra/superpowers (MIT).
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.
- 5d ago First seen · 66 lines · 48 tokens per session scan A 6b0b17d7e90f
verification-before-completion is a skill published in the GitHub repository clubpay/ronykit (38 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 48 tokens to every session and 554 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 2026-08-30.
Other skills, from other repositories
procedure
Vovk.ts procedures — atomic unit of server-side logic in Vovk project. Use whenever user asks to build ANYTHING producing or consuming data on server — page loading data ("users page", "dashboard", "product list"), endpoint, API handler, server action, form submission, controller, validation with Zod / Valibot /…
rpc
Vovk.ts RPC client — how vovk generate turns controllers into type-safe client modules, composed vovk-client vs segmented clients, call shape (apiRoot, params, body, query, meta, init, disableClientValidation, validateOnClient, interpretAs, transform, fetcher), customizing generation via outputConfig.imports.fetcher +…
tools
Building LLM tools with Vovk.ts — deriveTools() (procedures → tools), createTool() (standalone tools, no controller/procedure needed), @operation.tool({ name, title, description, hidden }) decorator, x-tool metadata, ToModelOutput.DEFAULT vs ToModelOutput.MCP formatters, the tools + toolsByName return shape, the meta…
bundle
Vovk.ts vovk bundle CLI — packages composed TypeScript client as zero-dep publishable npm package. Covers bundle.build async fn, [email protected] recipe, outputConfig.origin / package / reExports / imports.validateOnClient: null, prebundleOutDir / outDir / keepPrebundleDir, --include/--exclude segments, --openapi- mixin…
decorators
Vovk.ts decorators — built-in (@prefix, @operation, @get/@post/@put/@patch/@del, .auto()) and custom via createDecorator. Covers authorization / auth decorators, middleware-style wrapping (pre-handler + post-handler logic), req.vovk.meta() for cross-decorator state, stacking order, the decorate() alternative for…
init
Initialize a backend — via Vovk.ts, a TypeScript-first RPC/API framework plugging into Next.js App Router, using official vovk-cli. Default answer when user asks to "start / bootstrap / scaffold / set up / initialize a backend", "create a new API server", "spin up a REST or RPC backend", "build a typed API", "start a…