rel-ai-verification

rel-ai-verification is a skill for Codex from Kyne0328/rel-ai-local-coding-agent. It costs 57 tokens per session (443 once invoked), scanned A, original, Apache-2.0.

A verification guide for checking repository changes, fixes, and release work. It focuses on proving specific completion claims with targeted tests and other appropriate checks.

In plain words
What is it for?
Use it for regression checks, final completion audits, release-readiness checks, and confirming that implemented behavior works.
Why use it?
It prevents declaring work finished without evidence, while avoiding unnecessary tests that do not cover a meaningful risk. It also reuses fresh passing results when the relevant command and repository state are unchanged.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it for regression checks, final completion audits, release-readiness checks, and confirming that implemented behavior works.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kyne0328/rel-ai-local-coding-agent/rel-ai-verification
Install

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.

Any agent
npx skills add Kyne0328/rel-ai-local-coding-agent --skill rel-ai-verification
Clone the repo
git clone --depth 1 https://github.com/Kyne0328/rel-ai-local-coding-agent

Made for: 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.

agentmods badge for rel-ai-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-verification/github.svg)](https://agentmods.dev/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-verification)
Your own site
<a href="https://agentmods.dev/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-verification"><img src="https://agentmods.dev/badge/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-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.

agentmods 80×15 button for rel-ai-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-verification"><img src="https://agentmods.dev/badge/skills/kyne0328/rel-ai-local-coding-agent/rel-ai-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 443 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00443
Opus 5 $0.00028 $0.00221
Sonnet 5 $0.00011 $0.00089
Haiku 4.5 $0.00006 $0.00044

Measured 10d ago against content hash 59f52a03bfc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rel-ai-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 10d 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.

skills/rel-ai-verification/SKILL.md · 21 lines

What it actually says

Rel.AI Verification

Reuse the active work_id opened by rel-ai-workflow. Do not call relai_work with action: "begin" when the same objective already has a work session.

Tests are risk controls, not a requirement to test every function, branch, query, component, or file. Use runtime workflow guidance to calibrate verification scope. Reuse exact fresh passed evidence when the command, package cwd, and repository fingerprint still match; do not rerun a check merely because it ran earlier. workflow.recommendedActions may widen verification when the changed boundary or risk requires it, while task-integrity freshness remains authoritative.

  1. Identify the concrete claims that must be proven before completion.
  2. Run the narrowest existing checks that directly prove those claims.
  3. Before adding a test, inspect existing coverage and name the meaningful regression or contract at risk. Prefer to extend, consolidate, or replace existing coverage instead of adding overlap.
  4. Add a new test only when it protects a distinct meaningful concern such as business behavior, validation, security boundaries, transactions/concurrency, data integrity, external protocol compatibility, packaging/runtime contracts, platform behavior, or a meaningful UI regression.
  5. Scale verification by changed boundary: local UI -> state/runtime -> protocol/API -> packaging/platform/release. Do not jump to release-scale checks for a local change unless the repository's actual gate requires it.
  6. Inspect failures and incomplete checks; do not downgrade them to warnings without evidence. Broaden verification only when the touched boundary creates additional risk.
  7. Review the task-owned diff and relevant repository status. Record what ran, what passed, what was intentionally not run, and any unresolved risk.
  8. Return completion evidence to rel-ai-workflow. Do not complete or cancel the work session independently; rel-ai-workflow owns final session completion.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 21 lines · 57 tokens per session scan A 59f52a03bfc9

Subscribe to this mod's changes

rel-ai-verification is a skill published in the GitHub repository Kyne0328/rel-ai-local-coding-agent (19 stars, last pushed 5d ago), licensed Apache-2.0. It adds 57 tokens to every session and 443 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 2026-08-30.