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 Kyne0328/rel-ai-local-coding-agent --skill rel-ai-verificationgit clone --depth 1 https://github.com/Kyne0328/rel-ai-local-coding-agentWrote 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/kyne0328/rel-ai-local-coding-agent/rel-ai-verification)<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.
<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>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 | $0.00057 | $0.00443 |
| Opus 5 | $0.00028 | $0.00221 |
| Sonnet 5 | $0.00011 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
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.
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.
- Identify the concrete claims that must be proven before completion.
- Run the narrowest existing checks that directly prove those claims.
- 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.
- 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.
- 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. - Inspect failures and incomplete checks; do not downgrade them to warnings without evidence. Broaden verification only when the touched boundary creates additional risk.
- Review the task-owned diff and relevant repository status. Record what ran, what passed, what was intentionally not run, and any unresolved risk.
- Return completion evidence to
rel-ai-workflow. Do not complete or cancel the work session independently;rel-ai-workflowowns final session completion.
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.
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.
- 10d ago First seen · 21 lines · 57 tokens per session scan A 59f52a03bfc9
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.
Other skills, from other repositories
test-router
A testing skill that chooses which checks to run based on the type, scope, and risk of a change.
dev-testing
A testing guide that defines when to use unit, integration, API, and end-to-end tests. Unit tests check small pieces of code, while end-to-end tests check a full user flow.
release-verification
A release-verification checklist for software versions and packages. It covers changelogs, tests, packaging, installation smoke checks, version-control actions, publishing, and checks after release.
host-contract-verification
A verification procedure for the rules between a host system and its hooks, command-line tools, startup scripts, workspace checks, visible responses, and fallback connections to MCP servers.
api-verification
An API verification workflow that creates both an .http request file and a .cjs JavaScript file, then runs an automation script to test them. An API is an interface through which software exchanges requests and responses.
consumer-validation-engineering
A validation workflow for checking a software package across separate repositories. It covers SDKs, command-line tools, frameworks, and shared packages using both linked source code and the packaged artifact users install.