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.
npx skills add New1Direction/korgex --skill verifiable-orchestrationgit clone --depth 1 https://github.com/New1Direction/korgexWrote 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.
[](https://agentmods.dev/skills/new1direction/korgex/verifiable-orchestration)<a href="https://agentmods.dev/skills/new1direction/korgex/verifiable-orchestration"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/verifiable-orchestration.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.00501 |
| Opus 5 | $0.00016 | $0.00251 |
| Sonnet 5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
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 8d 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.
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
Agenttool. Emit severalAgentcalls 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
Orchestratetool. Give itnodeswithdeps(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
seedtoOrchestrate— the agreed{goal, constraints, acceptance_criteria}. It's recorded as an immutable, hash-chainedspec.seedthe whole run anchors under, sokorgex why/tracewalk any result back to the spec it was meant to satisfy andkorgex verifyproves 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(andseed_seq) — trace from there to audit exactly what each subagent did and why.
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.
- 8d ago First seen · 36 lines · 32 tokens per session scan A 3238248acba5
verifiable-orchestration is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 501 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.
Other skills, from other repositories
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
omp
Bounded Oh My Pi (omp) provider shortcut via Elves. Use when the user says /omp or "use omp" for a one-shot task.
setup-cobbler
Configure Cobbler model routes and external-agent preferences for this checkout. Use when the user types /setup-cobbler, asks to set up Cobbler model routes, onboard models, or update which tools handle planning/implement/review in Claude Code.
claudexor
Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness…
fugu
Run a bounded Sakana Fugu repository task or explicit review through codex-fugu. Use when the user types /fugu, asks to use Fugu, or asks for a Fugu review.
elves-grok-bot
Unattended-run kernel for Grok Bot non-git work. Use when the user says "use elves" for a long unattended job with no PR/merge model.