agentmods.dev

verifiable-orchestration

verifiable-orchestration is a skill for Claude Code, Codex from New1Direction/korgex. It costs 32 tokens per session (501 once invoked), scanned A, original, MIT.

A method for coordinating several coding agents as one traceable dependency graph. A dependency graph records which tasks can run together and which must wait for earlier tasks.

In plain words
What is it for?
It helps split independent work across agents, order dependent tasks such as exploration, planning, implementation, and review, and record the agreed goal and acceptance criteria.
Why use it?
It makes multi-agent work easier to audit and replay, while preventing tasks from continuing when a required earlier task failed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

not rated 5repo 24d ago A scan 32 tokens original MIT

Good fit It helps split independent work across agents, order dependent tasks such as exploration, planning, implementation, and review, and record the agreed goal and acceptance criteria.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/new1direction/korgex/verifiable-orchestration
View source ↗ New1Direction/korgex korgex-docs.pages.dev
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 New1Direction/korgex --skill verifiable-orchestration
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

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 verifiable-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/new1direction/korgex/verifiable-orchestration/github.svg)](https://agentmods.dev/skills/new1direction/korgex/verifiable-orchestration)
Your own site
<a href="https://agentmods.dev/skills/new1direction/korgex/verifiable-orchestration"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/verifiable-orchestration/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.

agentmods 80×15 button for verifiable-orchestration

Your own site · 80×15
<a href="https://agentmods.dev/skills/new1direction/korgex/verifiable-orchestration"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/verifiable-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 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.
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 $0.00032 $0.00501
Opus 5.5 $0.00013 $0.00200
Sonnet 5.5 $0.00006 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 2mo ago against content hash 3238248acba5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verifiable-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 2mo 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.

src/skills_builtin/verifiable-orchestration/SKILL.md · 36 lines

What it actually says

korgex can split work across subagents and record the whole run as one connected, tamper-evident causal DAG — replayable and auditable (korgex trace/verify). Pick the right shape:

  • Independent, flat sub-tasks → the Agent tool. Emit several Agent calls in ONE turn and they fan out concurrently (results return in order; a crashed sibling is isolated). Use for "explore these 3 areas", "review these 4 files".
  • Sub-tasks with DEPENDENCIES → the Orchestrate tool. Give it nodes with deps (e.g. explore → plan → implement → review): independent nodes run in parallel, a node waits for its deps, and if a node fails its dependents are skipped rather than run against a broken precondition. The whole run — including the failure topology — is one verifiable DAG.

Lock intent first, for non-trivial runs:

  • Pass seed to Orchestrate — the agreed {goal, constraints, acceptance_criteria}. It's recorded as an immutable, hash-chained spec.seed the whole run anchors under, so korgex why/trace walk any result back to the spec it was meant to satisfy and korgex verify proves the spec wasn't altered after the fact. Use it whenever the "what we agreed to build" should be pinned before work starts.

Rules:

  • One level deep. A subagent cannot itself spawn agents or orchestrate (hard-enforced) — keep the graph at the top level.
  • Each node gets a tool surface scoped to its type (explore/plan/review/research are read-only; code gets the full set).
  • Prefer a few well-scoped nodes over many tiny ones; name dependencies explicitly.
  • After the run, the result carries root_seq (and seed_seq) — trace from there to audit exactly what each subagent did and why.
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. 2mo ago First seen · 36 lines · 32 tokens per session scan A 3238248acba5

Subscribe to this mod's changes

verifiable-orchestration is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 24d ago), licensed MIT. It adds 32 tokens to every session and 501 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agentsCode reviewai-agentautonomous-codingcloud-sandboxcoding-agentdeveloper-tools
Related

verifiable-orchestration compared with skills from other repositories

verifiable-orchestration next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verifiable-orchestrationNew1Direction/korgexSkill524d agoMITA32Claude Code, Codex
vibe-securityxushuodasd/VIBE-Claude-PluginSkill44mo agoMITA49Claude Code
vibe-reviewxushuodasd/VIBE-Claude-PluginSkill44mo agoMITA22Claude Code
autofix-prQwenLM/qwen-codeSkill29kyesterdayApache-2.0A141Claude Code
gh-find-prsHmbown/CodeWhaleSkill41k6d agoMITA27Claude Code, Codex
reviewHmbown/CodeWhaleSkill41k6d agoMITA73Claude Code, Codex
simplifyQwenLM/qwen-codeSkill29kyesterdayApache-2.0A63Claude Code, Codex