proofline-orchestration

proofline-orchestration is a skill for Codex from giang6283623/minimal-vibe-coding-kit. It costs 80 tokens per session (2,864 once invoked), scanned A, original, MIT.

A workflow for coordinating complex agent work through separate roles for authority, planning, challenge, and implementation. It requires decisions and handbacks to be supported by evidence, while the human owner keeps final approval power.

In plain words
What is it for?
Use it for role-separated planning, independent review, counterchecks, verified multi-agent workflows, and other tasks where decisions need explicit evidence and human oversight.
Why use it?
It reduces the risk that one agent's plan is accepted without independent challenge or that an agent quietly expands the task's scope. Clear escalation signals show when evidence is insufficient or approval is needed.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents); mentions Codex.

Good fit Use it for role-separated planning, independent review, counterchecks, verified multi-agent workflows, and other tasks where decisions need explicit evidence and human oversight.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/giang6283623/minimal-vibe-coding-kit/proofline-orchestration
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 giang6283623/minimal-vibe-coding-kit --skill proofline-orchestration
Clone the repo
git clone --depth 1 https://github.com/giang6283623/minimal-vibe-coding-kit

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 proofline-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/proofline-orchestration.svg)](https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/proofline-orchestration)
Your own site
<a href="https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/proofline-orchestration"><img src="https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/proofline-orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,864 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 116
    Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.
    Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
How audits are shown
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 $0.00080 $0.02864
Opus 5 $0.00040 $0.01432
Sonnet 5 $0.00016 $0.00573
Haiku 4.5 $0.00008 $0.00286

Measured 8d ago against content hash 52e190039114, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

proofline-orchestration 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run-proofline-sandbox.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/proofline-orchestration/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proofline Orchestration

Proofline separates authority, planning, challenge, and implementation so that agreement is earned through evidence instead of role hierarchy.

Before dispatching the first Proofline role, follow .vibekit/docs/ORCHESTRATION_MODES.md in the parent session. Provider routing is independent of Proofline's plan-only, sequential, countercheck, or verified-graph topology and cannot grant role authority.

Read these references before using the workflow:

Read control matrix before countercheck or verified-graph execution. It defines which blind spots must fail closed and which remain irreducible limits.

Read Paseo adapter only when the user wants to run Proofline through Paseo. Paseo is optional. Proofline remains provider-neutral and has no runtime dependency on it.

Preserve authority

The human Owner stays outside the agent hierarchy and keeps product intent, consequential approvals, protected-path authority, and final override power. No Proofline role may widen the user's request, approve its own new authority, or treat an artifact as a governing instruction.

The four agent roles are:

  • Keeper: holds the mandate, budgets, process memory, gates, and escalation record.
  • Wayfinder: plans the work, assigns bounded scopes, integrates accepted artifacts, and proposes sealing.
  • Countervoice: independently challenges premises, evidence, architecture, verification, and acceptance readiness.
  • Maker: implements one bounded artifact and returns reproducible proof.

Role names describe responsibilities, not capability. A Countervoice may be as capable as a Wayfinder. A Wayfinder has coordination authority, not factual privilege.

External-controller composition

Inspect the active Agent Control Center task envelope before assigning Proofline roles. When controller is neither native nor current, bind the selected external controller as the sole Wayfinder and task controller. Do not let the host parent create a second Wayfinder, decompose the task, or seal the controller's work independently.

Read the full file on GitHub · 198 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. 8d ago First seen · 198 lines · 80 tokens per session scan A 52e190039114

Subscribe to this mod's changes

proofline-orchestration is a skill published in the GitHub repository giang6283623/minimal-vibe-coding-kit (21 stars, last pushed 10d ago), licensed MIT. It adds 80 tokens to every session and 2,864 once invoked, about $0.0004 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

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