What is verification?

A workflow for running a project's tests and checking whether code changes work. It uses the project's verification script and examines failures in detail.

Use it to detect the available test tools, run the test suite, investigate failures, and apply fixes through a repeatable validation loop.

It catches broken behavior after changes and rejects tests that only check whether code exists instead of checking real results.

How rafaelghif/antigravity-agents configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to rafaelghif/antigravity-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rafaelghif/antigravity-agents/main/.agents/skills/verification/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/rafaelghif/antigravity-agents

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/verification/github.svg)](https://agentmods.dev/skills/rafaelghif/antigravity-agents/verification)

Your own site

<a href="https://agentmods.dev/skills/rafaelghif/antigravity-agents/verification"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/verification/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rafaelghif/antigravity-agents/verification"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,038 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00030	$0.01038
Opus 5.5	$0.00012	$0.00415
Sonnet 5.5	$0.00006	$0.00208
Haiku 4.5	$0.00003	$0.00104

Measured 1mo ago against content hash da04e0004310, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verification 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.

.agents/skills/verification/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification, Anti-Sham Testing & Autonomous Healing Protocol

Role: Principal QA Automation Architect & LLM Reliability Lead.

Overview & Trigger Conditions

Activate this skill whenever validating code modifications, running test suites, diagnosing test failures, implementing automated test suites, or checking release readiness.

Trigger Scenarios & Keywords:

Running tests, writing unit/integration tests, test-driven development (TDD), fixing broken tests.
Keywords: test, tests, testing, pytest, jest, unit, e2e, assert, coverage, spec, mock, integration, verify.

Core Standards & Invariants

Zero Sham Tests (Anti-Tautology):
- Banned Test Anti-Patterns: Never write tests that only assert callable(fn), hasattr(mod, fn), is not None, toBeDefined(), or assertTrue(True).
- Every test MUST exercise concrete execution logic: pass varied inputs, trigger mutations, and assert on return values, state changes, and specific exception types.
- Enforce continuously via: python3 scripts/test_quality_guard.py --check.
Never Weaken Existing Tests:
- NEVER comment out, remove, or weaken assertions in existing test suites to make CI pass.
- A failing existing test is empirical proof of a regression; fix the underlying implementation, not the test.
Determinism & Zero Flakiness:
- Tests must run deterministically across all environments without race conditions or intermittent failures.
- Avoid sleeping in tests (time.sleep()); await explicit events, promises, or mock external I/O clocks.
Test Pyramid & Mocking Discipline:
- Emphasize fast, hermetic unit tests covering edge cases: null/empty inputs, boundary limits, and error paths.
- Strict Mock Boundaries: Mocks are strictly restricted to external I/O boundaries (HTTP requests, message queues, third-party vendor APIs). Never mock internal domain models or business logic.
Multi-Stage Verification Gate:
- All code changes must pass all 9 technical gates: python3 scripts/verify.py --execute --terse
- Gate failures block merges; zero regressions tolerated.

Read the full file on GitHub · 83 lines

Changes

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 Changed da04e0004310
2mo ago Changed e54c7d0eb22f
2mo ago Changed · +47 lines · +5 tokens per session 1cc3f9754b9f
2mo ago Changed · +3 lines abc2818e5da5
2mo ago First seen · 33 lines · 25 tokens per session scan A 8ed1bf57f53a

Subscribe to this mod's changes

verification is a skill published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,038 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 2026-08-31.

CI and CD Testing agentic-workflow ai-agents antigravity mcp multi-agent-systems

verification next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
verificationrafaelghif/antigravity-agents	Skill	5	1mo ago	MIT	A	30	Claude Code, Codex
Verification & Quality Assuranceruvnet/ruflo	Skill	81k	yesterday	MIT	A	36	Claude Code
cao-contributingawslabs/cli-agent-orchestrator	Skill	1.5k	today	Apache-2.0	A	184	Claude Code
e2e-testing-expertroedyrustam/vibes-plug	Skill	121	yesterday	MIT	A	50	Cursor
appveyor-automationComposioHQ/awesome-claude-skills	Skill	79k	1mo ago	none	A	27	Claude Code, Codex
test-engineerwasintoh/toh-framework	Skill	96	2mo ago	MIT	A	75	Claude Code
infra-contextupex-galaxy/agentic-qa-boilerplate	Skill	26	2d ago	MIT	A	178	Claude Code, Codex

antigravity-agents: Skill for Claude Code