verify-lanes

verify-lanes is a skill for Claude Code from leifericf/agentic-sdk. It costs 39 tokens per session (1,164 once invoked), scanned A, original, MIT.

A verification procedure that runs a project's configured checks in three levels: cheap checks after edits, wave checks during review, and pre-land checks before merging or tagging.

In plain words
What is it for?
Use it to run the selected verification tier, stop at the first failure, and report which checks passed, failed, or were skipped.
Why use it?
It makes verification consistent and reports missing or unwired checks instead of treating incomplete coverage as a pass.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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.

agentmods
npx agentmods add skills/leifericf/agentic-sdk/verify-lanes
Any agent
npx skills add leifericf/agentic-sdk --skill verify-lanes
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code.

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 verify-lanes

README.md
[![agentmods](https://agentmods.dev/badge/skills/leifericf/agentic-sdk/verify-lanes.svg)](https://agentmods.dev/skills/leifericf/agentic-sdk/verify-lanes)
Your own site
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/verify-lanes"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/verify-lanes.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,164 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.01164
Opus 5 $0.00019 $0.00582
Sonnet 5 $0.00008 $0.00233
Haiku 4.5 $0.00004 $0.00116

Measured 6d ago against content hash 63ff16b3f6f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verify-lanes 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 6d 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/verify-lanes/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verify-lanes

Role: run the project's deterministic lanes and report a verdict.

The lane table is descriptor data, never hardcoded commands. Read ~/.agentic-sdk/<project>/project.edn's :lanes map (see skills/shared/references/project-descriptor.md): three tiers, each a vector of shell command strings run in vector order, stopping on the first failure.

  • :cheap runs on every unit and after every edit. The tight loop; it carries only what must gate each landing.
  • :wave runs once per review round, once per integrated wave. The slower tier that justifies a wave, not a tight loop.
  • :pre-land runs before a land and before a tag. The gate the require-tests-before-land hook arms on.

A tier absent or empty in the descriptor reports SKIP <tier>: not configured. A command not yet wired (no build file, no test runner) reports SKIP <lane>: not yet wired so the verifier is honest about coverage gaps rather than silently passing.

How to run

Run each tier's commands in order, in the project root. The dispatch names the tier (:cheap, :wave, or :pre-land); run only that tier unless told to run all. On failure, capture the first error line and the repro command, then stop the tier (unless dispatched with "run all").

Keep the cheap tier fast

The cheap tier runs many times per slice; its wall-clock is paid repeatedly, so it carries only what must gate each landing, never the expensive checks a wave or pre-land boundary can carry once.

  • Owned tests, not the full suite, in the cheap tier. Scope the test command to the touched module when the descriptor's lane allows it; the full suite belongs to the wave and pre-land.
  • Reduced property case counts in the cheap tier; full count at the wave. The property is unchanged; only how many cases the inner loop samples.
  • Coverage and cross-build canaries are per-wave or pre-land, never per-unit. They instrument or re-run the whole suite; a per-unit run is wall-clock the boundary should have absorbed.
  • Amortize startup where a persistent process is available (a long-lived test runner, an nREPL, a REPL). A cold process per lane pays fixed startup every time and buys no rigor.

Read the full file on GitHub · 116 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.

  1. 6d ago First seen · 116 lines · 39 tokens per session scan A 63ff16b3f6f6

Subscribe to this mod's changes

verify-lanes is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 1,164 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens