Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/telus-labs/stagecraftnpx agentmods add skills/telus-labs/stagecraft/verification-beyond-testsWrote 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/telus-labs/stagecraft/verification-beyond-tests)<a href="https://agentmods.dev/skills/telus-labs/stagecraft/verification-beyond-tests"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/verification-beyond-tests/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/telus-labs/stagecraft/verification-beyond-tests"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/verification-beyond-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 110 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00067 | $0.02208 |
| Opus 5 | $0.00034 | $0.01104 |
| Sonnet 5 | $0.00013 | $0.00442 |
| Haiku 4.5 | $0.00007 | $0.00221 |
Grade A, and why
verification-beyond-tests 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 9d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification beyond tests — five phases
Unit tests prove the cases the author thought of. The cases nobody thought of remain unverified. This skill applies systematic verification methods to make the unverified surface smaller — without pretending to verify things that aren't verifiable.
When to use
You're authoring stage-06d (verifier role). Stage-06 (qa) already
returned PASS — the floor is in place. The track is full, so the
expectation is rigour over speed. Your task: pick the right method per
candidate, apply it, surface findings.
Phase 1 — Inventory candidates
Scan the diff. For each function/module, classify against the methods:
| Code shape | Method |
|---|---|
| Pure functions over structured data — parsers, validators, codecs, transforms, sort/dedupe, math, normalisation | Property-based |
| Custom formatters, serializers, or encoders over user-controlled data — logging formatters, structured log schemas, metric label builders, trace attribute setters | Property-based (valid-output invariant: output is parseable/well-formed for all inputs up to the field's documented max) |
| Critical business logic with example tests — auth, billing, anything with a real test suite | Mutation |
| Concurrent state machines, distributed protocols, consistency invariants, security properties | Formal |
| Glue, UI, CRUD with thin logic | Skip with reason |
Write the inventory as a table in the report. Be honest about glue — applying mutation to a thin CRUD wrapper produces theatre, not signal.
Caution on the "glue" classification for observability code. Logging formatters and structured log helpers look like glue but are serializers over user-controlled input. Python's logging.Handler.emit(), Go's slog handlers, Java's Appender.append(), and equivalent frameworks catch formatter exceptions internally — a NameError, KeyError, or encoding error in the formatter is written to stderr and the application continues normally. HTTP-response tests cannot detect this failure mode; the service returns correct responses while silently dropping every log line. Classify custom log formatters as codecs, not glue. The property to assert is the valid-output invariant: for all inputs up to the field's max length, the formatted output must be parseable by the target consumer.
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.
- 9d ago First seen · 202 lines · 67 tokens per session scan A b480bf6f8799
verification-beyond-tests is a skill published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 2,208 once invoked, about $0.0003 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
intuitive-tests
Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…
verify
Run the HUMHUM quality gates that are actually touched by the current diff — frontend typecheck + vitest, and Rust fmt/clippy/test — mirroring CI. Use before marking work done, opening a PR, or when asked to "verify", "check", or "run the gates".
test-generation
Generate comprehensive tests for code including unit tests, integration tests, and edge case coverage. Analyzes code to identify testable units and generates tests matching the project's testing framework and conventions.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.