orchestration-verification

orchestration-verification is a skill for Claude Code, Codex from chankov/agent-fleet. It costs 93 tokens per session (3,270 once invoked), scanned A, original, MIT.

A verification process for work coordinated by multiple AI agents. It turns requirements into checkable statements, tracks special cases when copying existing behavior, and requires evidence for completion.

In plain words
What is it for?
Use it to define acceptance checks, inventory behavior that must match an existing example, require structured status reports, and rerun checks when requirements change.
Why use it?
It addresses the risk that agents report success without actually testing every requirement. It also helps prevent requirements from being lost as work passes between agents.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/chankov/agent-fleet/orchestration-verification
Any agent
npx skills add chankov/agent-fleet --skill orchestration-verification
Clone the repo
git clone --depth 1 https://github.com/chankov/agent-fleet

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.

agentmods badge for orchestration-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/chankov/agent-fleet/orchestration-verification.svg)](https://agentmods.dev/skills/chankov/agent-fleet/orchestration-verification)
Your own site
<a href="https://agentmods.dev/skills/chankov/agent-fleet/orchestration-verification"><img src="https://agentmods.dev/badge/skills/chankov/agent-fleet/orchestration-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,270 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 $0.00093 $0.03270
Opus 5 $0.00046 $0.01635
Sonnet 5 $0.00019 $0.00654
Haiku 4.5 $0.00009 $0.00327

Measured 5d ago against content hash 8fa349d1241a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

orchestration-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 5d 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.

.versions/0.0.1/skills/orchestration-verification/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestration Verification — the Verification Contract

Overview

Multi-agent runs drop clearly stated requirements silently. The dispatcher relays the requirement as prose, specialists return prose summaries ("approved", "verification passed"), and the feature ships broken anyway. Propagation is rarely the problem — the requirement is usually right there in the dispatch text. Verification is the problem: nothing exercised the requirement and refused "done" until it passed.

This skill defines the four artifacts that replace prose-as-truth with checkable assertions and named evidence. It is the single canonical source for their formats — orchestrator and specialist personas reference this skill by name instead of restating the schema.

  1. Acceptance assertions — the dispatcher converts the request into numbered, individually checkable statements before any builder runs.
  2. Parity / touchpoint inventory — for "make X behave like existing Y", an exhaustive list of every site where the exemplar is special-cased; each becomes an assertion.
  3. Structured upward return — specialists report assertion status with evidence, never a prose verdict.
  4. Requirement-regression reset — on "it's wrong again", stale summaries are invalidated and the assertion set rebuilt from the latest correction before re-dispatch.

When to Use

  • Orchestrating specialists through a dispatcher (e.g. the agent-hub harness) on anything beyond a trivial single read.
  • A "make X behave like existing Y" request — the parity failure (exemplar implemented, siblings missed) is the dominant multi-agent defect this skill targets.
  • UI / visibility / placement work, where a static review can approve a runtime that is actually broken.
  • A requirement that has already shipped wrong once — trigger the regression reset before dispatching again.

When NOT to use: single-agent trivial changes, pure reconnaissance, or conversational tasks with no implementation.

Process

Read the full file on GitHub · 182 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. 5d ago First seen · 182 lines · 93 tokens per session scan A 8fa349d1241a

Subscribe to this mod's changes

orchestration-verification is a skill published in the GitHub repository chankov/agent-fleet (13 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 3,270 once invoked, about $0.0005 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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 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