verification-orchestrator

verification-orchestrator is a skill for Claude Code, Codex from QinxiangCao/QualifiedCProgramming. It costs 70 tokens per session (619 once invoked), scanned A, original, MIT.

A controller procedure for managing a complete C verification run, from setup and annotation work through proof checks, merging, and final validation.

In plain words
What is it for?
Use it to run the full verification workflow, manage annotation and proof workers, collect specification gaps, merge approved changes, and perform the final check.
Why use it?
It coordinates several verification roles and preserves the required order of their work, reducing the risk of incomplete or conflicting results.

Skill for Claude CodeCodex

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/qinxiangcao/qualifiedcprogramming/verification-orchestrator
Any agent
npx skills add QinxiangCao/QualifiedCProgramming --skill verification-orchestrator
Clone the repo
git clone --depth 1 https://github.com/QinxiangCao/QualifiedCProgramming

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 verification-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/qinxiangcao/qualifiedcprogramming/verification-orchestrator.svg)](https://agentmods.dev/skills/qinxiangcao/qualifiedcprogramming/verification-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/qinxiangcao/qualifiedcprogramming/verification-orchestrator"><img src="https://agentmods.dev/badge/skills/qinxiangcao/qualifiedcprogramming/verification-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 619 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 $0.00070 $0.00619
Opus 5 $0.00035 $0.00309
Sonnet 5 $0.00014 $0.00124
Haiku 4.5 $0.00007 $0.00062

Measured 4d ago against content hash 849751918842, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verification-orchestrator 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 4d 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.

.agents/skills-en/verification-orchestrator/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Orchestrator

Use only as the main agent. Treat controller_state.json and the action returned by the controller as authoritative; do not call an internal module directly, implement a state transition yourself, or modify owner files on an owner's behalf.

Main executes every invocation carried by an action verbatim, maintains the mapping from controller owners to agent targets, and sends each claim response's fixed handoff.prompt verbatim to the corresponding agent. Spawn the annotation agent only once per run and append every later repair to the same target; each vc-checking attempt and each group's first group-worker claim uses an independent session.

Main's proactive read boundary consists only of:

  • this skill and every workflow/doc listed below;
  • the current blocker, state summary, and handoff files explicitly provided by controller actions;
  • when the controller reaches final-check, final-check/SKILL.md and its workflow;
  • on Windows, the repository-root AGENTS_WIN.md and the Windows adaptation guide to which it routes.

Main does not read, summarize, or reinterpret owner skills such as annotation-filling, annotation-checking, vc-checking, or group-worker-proving. Each owner reads only its own skill and the current handoff files according to the verbatim claim message; main orchestrates and does not learn role-specific knowledge on an owner's behalf. vc-proving is not a phase subagent: the controller drives group preparation, aggregation, merge, and parent verification.

When there is no manual VC, skip vc-checking and group-workers but still perform the controller-selected dependency preparation (whose public action name remains dune-build), parent verification, writeback, and final checks. When groups exist, keep dispatching every group in the round even after a group reports an annotation gap; enter one aggregated annotation retry only after every group reaches a terminal state, and do not merge or verify that round.

Read the full file on GitHub · 31 lines

Files

What ships with it

5 files 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. 4d ago First seen · 31 lines · 70 tokens per session scan A 849751918842

Subscribe to this mod's changes

verification-orchestrator is a skill published in the GitHub repository QinxiangCao/QualifiedCProgramming (43 stars, last pushed 14d ago), licensed MIT. It adds 70 tokens to every session and 619 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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