subagent-prompting

subagent-prompting is a skill for Claude Code from ashaykubal/essential-agents-skills. It costs 49 tokens per session (2,399 once invoked), scanned A, a copy of subagent-prompting, MIT.

A four-part template for giving software agents clear tasks, limits, background information, and output requirements.

In plain words
What is it for?
Use it when coordinating specialist agents, designing multi-step agent workflows, or requiring consistent results from each stage.
Why use it?
It makes agent requests more predictable and reduces confusion about what the agent should do or return.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Good fit Use it when coordinating specialist agents, designing multi-step agent workflows, or requiring consistent results from each stage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ashaykubal/essential-agents-skills/subagent-prompting
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 ashaykubal/essential-agents-skills --skill subagent-prompting
Clone the repo
git clone --depth 1 https://github.com/ashaykubal/essential-agents-skills

Made for: Claude Code.

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 subagent-prompting

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashaykubal/essential-agents-skills/subagent-prompting/github.svg)](https://agentmods.dev/skills/ashaykubal/essential-agents-skills/subagent-prompting)
Your own site
<a href="https://agentmods.dev/skills/ashaykubal/essential-agents-skills/subagent-prompting"><img src="https://agentmods.dev/badge/skills/ashaykubal/essential-agents-skills/subagent-prompting/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.

agentmods 80×15 button for subagent-prompting

Your own site · 80×15
<a href="https://agentmods.dev/skills/ashaykubal/essential-agents-skills/subagent-prompting"><img src="https://agentmods.dev/badge/skills/ashaykubal/essential-agents-skills/subagent-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,399 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 98% copy Near-identical to another mod 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 5.1 $0.00049 $0.02399
Opus 5 $0.00024 $0.01200
Sonnet 5 $0.00010 $0.00480
Haiku 4.5 $0.00005 $0.00240

Measured 11d ago against content hash e9df79593598, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

subagent-prompting 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 11d 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.

Origin

This is a copy

98% identical to subagent-prompting — 732 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/subagent-prompting/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sub-Agent Prompting Template

Overview

This skill provides a standardized template for invoking sub-agents with deterministic inputs and predictable outputs. Use this when:

  • Orchestrating specialist sub-agents (code auditor, test auditor, etc.)
  • Designing multi-agent workflows with conditional branching
  • Ensuring consistent prompt structure across sub-agent invocations

4-Part Template (Required)

Every sub-agent invocation MUST include all four parts. Incomplete prompts lead to unpredictable behavior.

GOAL (What Success Looks Like)

State the high-level objective, not just the action. Good goals are outcome-focused.

## GOAL

[Describe the desired end state, not the process]

Examples:
- GOOD: "Identify all security vulnerabilities that could allow unauthorized data access"
- BAD: "Review the auth file"

- GOOD: "Refactor authentication module for improved maintainability without breaking existing tests"
- BAD: "Refactor the code"

CONSTRAINTS (What You Cannot Do)

Explicit boundaries prevent scope creep and unexpected changes.

## CONSTRAINTS

- [Hard limit 1: e.g., "Do NOT modify any files"]
- [Hard limit 2: e.g., "Do NOT add new dependencies"]
- [Hard limit 3: e.g., "Maintain backward API compatibility"]
- [Resource limit: e.g., "Complete within 50 tool calls"]

Examples:
- "Identify issues only - do NOT implement fixes"
- "Read-only analysis - no file modifications"
- "Focus only on files in src/auth/ directory"

CONTEXT (What You Need to Know)

Provide all information required to complete the task. Sub-agents run in isolated context and cannot access parent conversation.

## CONTEXT

### Files to Analyze
- `path/to/file1.ts` - [brief description of relevance]
- `path/to/file2.ts` - [brief description of relevance]

### Related Context
- Previous findings: [summary of relevant prior work]
- Architecture notes: [relevant design decisions]
- Known issues: [existing problems to be aware of]

### Standards to Apply
- [Coding standard or guideline reference]
- [Security policy reference if applicable]

Read the full file on GitHub · 365 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 365 lines · 49 tokens per session scan A e9df79593598

Subscribe to this mod's changes

subagent-prompting is a skill published in the GitHub repository ashaykubal/essential-agents-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 2,399 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to subagent-prompting, differing in 732 lines, and is treated as a copy.

Related

Other skills, from other repositories

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens