pixir-delegate-native

Instructions for delegating work to subagents from inside a Pixir session. Subagents are separate workers that can handle parts of a task in parallel.

In plain words
What is it for?
Use them when an active Pixir session needs parallel workers, follow-up input to a worker, status checks, or repeatable skill-based workflows.
Why use it?
They provide the correct Pixir-native controls for starting, waiting for, guiding, checking, and closing those workers.

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/ranvier-technologies/pixir/pixir-delegate-native
Any agent
npx skills add Ranvier-Technologies/pixir --skill pixir-delegate-native
Clone the repo
git clone --depth 1 https://github.com/Ranvier-Technologies/pixir

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 723 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 $0.00089 $0.00723
Opus 5 $0.00044 $0.00362
Sonnet 5 $0.00018 $0.00145
Haiku 4.5 $0.00009 $0.00072

Measured 2d ago against content hash 2e9e94a21efb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pixir-delegate-native 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 2d 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/pixir-delegate-native/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pixir Delegate (native) — delegation from inside the runtime

You are already inside a Pixir session. The delegation judgment you follow is the shared core — read ../pixir-delegate/references/delegation-core.md on first use. This variant covers only what changes when the orchestrator IS a Pixir session.

First established by a blind run (session 20260705T001653-399094): an in-Pixir orchestrator correctly refused the CLI variant's own commands, because shelling out to pixir from inside Pixir boots the extra runtime layer the core doctrine forbids. Your actuation surface is the native tools.

Surface mapping

Core concept Native form
Fan-out spawn_agent × N (children share your VM)
Await + reconcile wait_agent, then list_agents for statuses/summaries
Steer or retry one child send_input to a live child; a finished child's session resumes like any session
Release close_agent when no follow-up is needed — completed agents count against concurrency until closed
Structured invocation skill-backed workflow templates (ADR 0013), when the delegation shape repeats

Concurrency is governed by the runtime's max_threads limit — children beyond it queue honestly. The parent wait horizon and per-child timeout are distinct knobs; a timed-out child is a resumable session, not a loss.

What this host changes about the practice

  • Rehearsal has no --dry-run analog on the native surface (known gap). Rehearse by validating your task contracts and child prompts before spawning: self-contained, strict-JSON output schema, read-only role for analysis. Spawn nothing you have not fully specified.
  • No hydration prologue: the !cmd`` line in the CLI variant renders inert here. Your runtime state is already yours — you know your version and session; verify workspace posture instead.
  • allowed-tools means nothing to this host: your tool authority comes from the session's permission mode and write policy, decided at session start, not from skill frontmatter.
  • Evidence is native: children are sessions with their own append-only logs; subagent_event references in your log plus the session tree (pixir tree from outside, or your own log fold) are the reconciliation record. Usage evidence lives in each child log's provider_usage events at .data.usage_summary.

Read the full file on GitHub · 57 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. 2d ago First seen · 57 lines · 89 tokens per session scan A 2e9e94a21efb

Subscribe to this mod's changes

pixir-delegate-native is a skill published in the GitHub repository Ranvier-Technologies/pixir (23 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 723 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

cross-linker

Scan the Obsidian wiki and automatically discover missing cross-references between pages. Use this skill when the user says "link my pages", "find missing links", "cross-reference", "connect my wiki", "add wikilinks", "what pages should be linked", or after any large ingestion to ensure new pages are woven into the…

saski/arnesto · 137 tokens

free-agent-execution

Run an explicitly requested, bounded, non-sensitive coding task through the local free-worker adapter using a verified free OpenCode model. Use only when the user asks to execute a free worker or free agent and accepts the external-model safety boundary.

saski/arnesto · 52 tokens

google-adk-agent-patterns

Define, compose, and wire Google ADK agents with function tools and multi-agent orchestration. Use when writing agent definitions, adding Python function tools, building pipelines with SequentialAgent/LoopAgent/ParallelAgent, or designing router/delegation patterns. Trigger on: adk agent, LlmAgent, SequentialAgent…

saski/arnesto · 92 tokens

corporate-aws-cli

Use when using the AWS CLI against a corporate AWS account after SAML/OIDC federation (e.g. saml2aws, aws sso login), when STS fails with invalid XML or empty responses, when selecting profiles or regions for Terraform or CI/CD stacks, or when validating RDS engine versions with describe-orderable-db-instance-options…

saski/arnesto · 81 tokens

google-adk-setup

Bootstrap a Google ADK (Agent Development Kit) project from zero to a running local dev UI. Use when setting up a new ADK agent project, configuring Vertex AI credentials, scaffolding the agent folder, or troubleshooting ADK environment issues. Trigger on: adk setup, adk init, google-adk, vertex ai agent, uv run adk…

saski/arnesto · 83 tokens

align

Presents a proposed approach in progressive confirmable chunks with recommended decisions and alternatives. Use when aligning on a design, plan, or technical approach before implementation.

saski/arnesto · 33 tokens