What is hierarchical?

A boss-and-worker method for dividing work among coding agents. The boss assigns tasks, workers submit their results, and the boss approves the work or requests changes.

Use it when one agent should delegate implementation tasks, review the results, request revisions, and give final approval.

It gives a team a clear chain of responsibility and a defined review loop. This helps prevent unfinished or unreviewed worker output from being treated as complete.

How dazzaji/interlateral_agents configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to dazzaji/interlateral_agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dazzaji/interlateral_agents/main/.agent/skills/hierarchical/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dazzaji/interlateral_agents

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/dazzaji/interlateral_agents/hierarchical/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/hierarchical)

Your own site

<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/hierarchical"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/hierarchical/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/dazzaji/interlateral_agents/hierarchical"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/hierarchical.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,155 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.01155
Opus 5.5	$0.00008	$0.00462
Sonnet 5.5	$0.00004	$0.00231
Haiku 4.5	$0.00002	$0.00115

Measured 1mo ago against content hash 89c0d82d19fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hierarchical 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 1mo 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.

.agent/skills/hierarchical/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hierarchical

Purpose

A structured delegation pattern where a boss agent assigns work to worker agents, reviews their output, and makes final approval decisions. Clear chain of command.

Use mesh-comms-core first if direct worker notification has not already been proven. comms.md is the ledger, not the wake-up path.

Default roster: use Claude Code and Codex peers. Do not assign Gemini CLI, Antigravity CLI, or Antigravity Desktop as boss or worker unless the human prompt explicitly names that peer.

Roles

Role	Description
`BOSS`	Delegates tasks, reviews work, approves or rejects
`WORKER`	Receives assignment, executes, submits for review

One BOSS, one or more WORKERs.

Protocol

1. DELEGATION: BOSS assigns specific tasks to each WORKER
2. EXECUTION: WORKERs complete their assigned tasks
3. SUBMISSION: WORKERs submit work with [SUBMIT]
4. REVIEW: BOSS reviews each submission
5. DECISION: BOSS signals [APPROVE] or [REVISE: feedback]
6. ITERATE: If revisions needed, WORKERs address and resubmit
7. COMPLETE: When all work approved, BOSS signals [DONE]

Delegation Format

[DELEGATION - BOSS]
@WORKER_1: [Task description]
@WORKER_2: [Task description]
DEADLINE: [Turn count or "when ready"]
ACCEPTANCE CRITERIA: [What "done" looks like]

Submission Format

[SUBMIT - WORKER]
TASK: [What was assigned]
DELIVERABLE: [The work product]
NOTES: [Any caveats or questions]

Review Format

[REVIEW - BOSS]
@WORKER: [APPROVE] or [REVISE]
FEEDBACK: [What's good, what needs work]

Inputs

All inputs come from the prompt.

Optional:

output: File path for final deliverable
work: File containing the overall goal
max_turns: Override default (30)

Prompt Format Examples

Minimal:

Use hierarchical to build a landing page.
CC is BOSS. CX and CC-peer-02 are WORKERs.

With specific tasks:

Use hierarchical for code review workflow.
BOSS=CC (Tech Lead).
WORKER=CX (implements feature).
WORKER=CC-peer-02 (writes tests).
Output: projects/feature/implementation.md

Read the full file on GitHub · 172 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.

1mo ago First seen · 172 lines · 19 tokens per session scan A 89c0d82d19fa

Subscribe to this mod's changes

hierarchical is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,155 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 2026-10-03.

Building agents

hierarchical next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hierarchicaldazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	19	Claude Code, Codex
imagegenopenai/codex	Skill	133k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

interlateral_agents: Skill for Claude Code