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.
npx skills add ashaykubal/essential-agents-skills --skill subagent-promptinggit clone --depth 1 https://github.com/ashaykubal/essential-agents-skillsWrote 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.
[](https://agentmods.dev/skills/ashaykubal/essential-agents-skills/subagent-prompting)<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.
<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>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 | $0.00049 | $0.02399 |
| Opus 5 | $0.00024 | $0.01200 |
| Sonnet 5 | $0.00010 | $0.00480 |
| Haiku 4.5 | $0.00005 | $0.00240 |
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.
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.
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]
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.
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.
- 11d ago First seen · 365 lines · 49 tokens per session scan A e9df79593598
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.
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.
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…
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.
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…
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.
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…