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 Kshitijpalsinghtomar/depth-skills --skill ds-verification-gatesgit clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-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/kshitijpalsinghtomar/depth-skills/ds-verification-gates)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-verification-gates"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-verification-gates/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/kshitijpalsinghtomar/depth-skills/ds-verification-gates"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-verification-gates.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 | $0.00046 | $0.04777 |
| Opus 5.5 | $0.00018 | $0.01911 |
| Sonnet 5.5 | $0.00009 | $0.00955 |
| Haiku 4.5 | $0.00005 | $0.00478 |
Grade A, and why
verification-gates 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 14d 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 — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VERIFICATION-GATES — Depth Verification Engine (Premium)
Mathematical Compliance: This skill implements the DEPTH-MATHEMATICS specification. It computes and outputs the final ADS, CEI, SI, EC, OV, and Depth . It runs all V1-V6 gates plus ungameable components. It is the final quality gate — no answer ships without passing.
Research Basis:
- Yao et al. (2023) "Tree of Thoughts: Deliberate Problem Solving with Large Language Models" (arXiv:2305.10601) — deliberate decision making with self-evaluation
- Liu et al. (2023) "Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge" (arXiv:2311.09731) — UnknownBench for calibration
- Shinn et al. (2023) "Reflexion: Language Agents with Verbal Reinforcement Learning" (arXiv:2303.11366) — self-correction with feedback
Every skill claims to verify something. DEEP-THINK verifies assumptions. ADVERSARY verifies opposition. PROVENANCE verifies evidence. But who verifies the verifiers?
This skill centralizes all verification. It runs after the full orchestration. It checks every gate with machine-checkable criteria. It runs ungameable components (human eval, held-out tasks, ensemble critic). It red-teams the gates themselves to detect gaming. It produces the **Depth ** — the single verifiable artifact of depth quality.
The Failure Mode You Must Recognize
You are about to deliver an answer that:
- Passed all skill-internal gates (but those gates were self-graded)
- Has beautiful cognitive traces (but they might be cargo cult)
- Claims high ADS (but the phase activations were self-reported)
- Has a Depth (but it wasn't independently verified)
This is verification theater — the appearance of rigor without the substance. Skills grade their own homework. Gates are checked by the same model that wants to pass them.
This skill breaks the cycle. It is the independent auditor. It re-runs gates with strict criteria. It runs ungameable components. It red-teams the verification itself. If it doesn't pass, the answer doesn't ship.
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.
- 14d ago First seen · 543 lines · 46 tokens per session scan A 8d8e8fc61c22
verification-gates is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 4,777 once invoked, about $0.0002 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 2026-10-03.
Other skills, from other repositories
verification-quality
Truth scoring, code-quality verification, and automatic rollback with a high accuracy threshold. Use when validating agent output before it ships, gating changes on quality, or adding a verify-and-rollback safety loop.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
ai-observability-promptfoo
Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.
desktop-testing-electron
E2E testing with Playwright, main process unit testing, IPC testing, dialog/menu mocking, CI headless setup.
mobile-testing-detox
Detox E2E gray-box testing for React Native - matchers, actions, expectations, waitFor, device API, synchronization, mocking, artifacts, CI integration.