orchestrator-context

orchestrator-context is a skill for Claude Code, Codex from dentiny/kon. It costs 38 tokens per session (1,167 once invoked), scanned A, original, MIT.

A rule for keeping the orchestrator's chat brief while storing detailed helper-agent results in files called artifacts. The chat uses file references instead of repeating the full results.

In plain words
What is it for?
Use it whenever commands launch subagents for team work, design, debugging, questions, research, reviews, or interactive-session routing.
Why use it?
It prevents long agent reports from filling the conversation and obscuring the current decision or next action.

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/dentiny/kon/orchestrator-context
Any agent
npx skills add dentiny/kon --skill orchestrator-context
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon

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 orchestrator-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/dentiny/kon/orchestrator-context.svg)](https://agentmods.dev/skills/dentiny/kon/orchestrator-context)
Your own site
<a href="https://agentmods.dev/skills/dentiny/kon/orchestrator-context"><img src="https://agentmods.dev/badge/skills/dentiny/kon/orchestrator-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,167 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 $0.00038 $0.01167
Opus 5 $0.00019 $0.00583
Sonnet 5 $0.00008 $0.00233
Haiku 4.5 $0.00004 $0.00117

Measured 4d ago against content hash fc5c796a0d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator-context 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 4d 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/orchestrator-context/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Context Contract

Owner: orchestrator Consumers: all /kon:* commands that spawn Task subagents (team, design, quick, debug, ask, research, review, begin routing, …)

Core principles (always): follow skills/core-principles — route by file pointer; don't restate or amplify subagent output (simplicity in orchestrator context).

Subagent Task returns enter the orchestrator's context window. Do not amplify bloat by quoting, restating, or forwarding that output in chat or in later spawn/resume prompts.

Full output lives in artifacts. Orchestrator holds pointers only.

Artifact map

Agent Full output artifact When
Orchestrator sessions/<SID>/understanding.md team, design, debug (orchestrator writes after pre-plan gate)
🎸 Azusa sessions/<SID>/explore.md /kon:team, /kon:design (subagentStop hook)
🎸 Azusa sessions/<SID>/debug.md /kon:debug (orchestrator writes once after Azusa)
📚 Jun .kon/research.md external research steps
🍰 Mugi PLAN_FILE (.kon/plan-<SID>.md or session plan) after plan step
📝 Mio sessions/<SID>/review.md team, quick, review, debug (subagentStop hook)
📝 Mio sessions/<SID>/pr-review.md /kon:review-pr
📚 Jun sessions/<SID>/issue-summary.md /kon:describe-issue
📋 Nodoka sessions/<SID>/summary.md /kon:summarize

Resolve paths:

SID="<session-id>"
SESSION_DIR=$(python3 $KON_ROOT/scripts/kon_session.py session-dir --id "$SID")
REVIEW_FILE=$(python3 $KON_ROOT/scripts/kon_session.py artifact-path --id "$SID" --name review.md)
EXPLORE_FILE=$(python3 $KON_ROOT/scripts/kon_session.py artifact-path --id "$SID" --name explore.md)

Orchestrator rules

  1. User-facing messages — one line per agent step (verdict + artifact path). Never paste subagent output into assistant messages.
  2. Next spawn / resume prompts — file pointers + milestone/delta only. Never forward must-fix lists, explore findings, or review bodies through the orchestrator.
  3. Impl-loop handoffs — Yui and Mio resume and read review.md directly. See skills/failure-handling.
  4. Plan approval — present goal + step/milestone count + ## Decisions needed bullets; do not dump the full plan into chat (user opens PLAN_FILE).
  5. After Task returns — call complete-agent with a one-sentence summary; do not copy the Task body into the summary field.

Read the full file on GitHub · 98 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. 4d ago First seen · 98 lines · 38 tokens per session scan A fc5c796a0d6e

Subscribe to this mod's changes

orchestrator-context is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,167 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens