What is paseo-orchestration?

A coordination guide for splitting complex work among multiple coding agents through Paseo. It covers choosing agent profiles, connecting dependent tasks, and handling requests between agents.

Creating and coordinating agent tasks, building dependency graphs, setting decision gates, and running coordinator loops.

It helps organize parallel work when a task is too large for one agent or when some tasks must wait for others. It also reduces errors from guessing which models or settings are available.

paseo-orchestration — Skill for Claude Code and Codex by wilgon456

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 wilgon456/Paseobility --skill paseo-orchestration

Clone the repo

git clone --depth 1 https://github.com/wilgon456/Paseobility

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wilgon456/paseobility/paseo-orchestration/github.svg)](https://agentmods.dev/skills/wilgon456/paseobility/paseo-orchestration)

Your own site

<a href="https://agentmods.dev/skills/wilgon456/paseobility/paseo-orchestration"><img src="https://agentmods.dev/badge/skills/wilgon456/paseobility/paseo-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wilgon456/paseobility/paseo-orchestration"><img src="https://agentmods.dev/badge/skills/wilgon456/paseobility/paseo-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,729 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: 2 findings, up to medium

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 →

medium Rogue Agent · line 6
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
low Privilege Escalation · line 84
Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00069	$0.01729
Opus 5	$0.00034	$0.00864
Sonnet 5	$0.00014	$0.00346
Haiku 4.5	$0.00007	$0.00173

Measured 10d ago against content hash 5b4e0e4993f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

paseo-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 10d 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.

skills/paseo-orchestration/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paseo Orchestration

Use Paseo's current agent, profile, workspace, schedule, and heartbeat tools to coordinate multiple agents. Read the base paseo skill first; it is the authority for exact tool schemas in the active installation.

Paseo 0.6 launch discovery

Do not guess provider, model, mode, thinking, or feature IDs.

Call list_profiles before creating agents and read every profile's notes.
If the user names a profile, use it. Otherwise choose the profile whose notes best match the delegated role.
There is no profile field on create_agent. Materialize the profile:
- combine provider and model as create_agent.provider
- copy modeId to settings.modeId
- copy thinkingOptionId to settings.thinkingOptionId
- copy featureValues to settings.features
If no profile fits, call list_providers, then inspect_provider. Call list_models only when model or thinking IDs are needed; the result can be large. Tell the user when no configured profile fits.
Only pass feature IDs returned by inspect_provider. For example, enable Codex fast mode only when fast_mode is advertised.

If ~/.paseo/orchestration-preferences.json exists, treat its free-form preferences as additional user guidance. Do not treat provider strings in that legacy file as current capability truth; validate them through the discovery tools above.

Core principles

Give every agent a self-contained prompt with task, context, paths, constraints, acceptance criteria, and expected output.
Use different providers when their strengths or an independent review are useful; do not force cross-provider work when one profile clearly fits.
Read-only workers may share a workspace. Writers that can overlap must use separate worktree workspaces.
Agent parentage and workspace placement are separate. A child created in a different workspace remains the caller's subagent.
Prefer asynchronous creation. Agent-scoped create_agent defaults notifyOnFinish to true; continue useful work and wait for the notification. Do not poll list_agents or get_agent_status merely to check progress.
Archive only agents and workspaces created for the workflow, and only when cleanup is part of the user's request or the workflow contract.

Read the full file on GitHub · 175 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.

10d ago First seen · 175 lines · 69 tokens per session scan A 5b4e0e4993f9

Subscribe to this mod's changes

paseo-orchestration is a skill published in the GitHub repository wilgon456/Paseobility (19 stars, last pushed 14d ago), licensed MIT. It adds 69 tokens to every session and 1,729 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.

Building agents Planning

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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