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 floomhq/moto --skill subagent-templatesgit clone --depth 1 https://github.com/floomhq/motoWrote 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/floomhq/moto/subagent-templates)<a href="https://agentmods.dev/skills/floomhq/moto/subagent-templates"><img src="https://agentmods.dev/badge/skills/floomhq/moto/subagent-templates.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.00788 |
| Opus 5 | $0.00037 | $0.00394 |
| Sonnet 5 | $0.00015 | $0.00158 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
subagent-templates 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Templates
When to Use Subagents
Good uses:
- Independent tasks that can run in parallel (QA checks, analysis, validation)
- Tasks requiring fresh context/perspective (reader testing, independent review)
- Large workloads that can be split by domain or file
- Verification tasks that should be independent from the author
Bad uses:
- Tasks with sequential dependencies (B must run after A finishes)
- Tasks requiring shared state that's hard to merge
- Simple tasks where coordination overhead exceeds benefit
Pattern 1: Parallel Analysis
Split a large analysis into independent slices, run in parallel, merge results.
TASK: Analyze codebase for security issues
SUBAGENTS:
- Agent A: Check authentication and authorization code
- Agent B: Check API input validation and sanitization
- Agent C: Check environment variables and secrets handling
- Agent D: Check dependency vulnerabilities
MERGE: Collect all findings, deduplicate, prioritize by severity
Pattern 2: Independent Verification
Have a fresh agent verify work without the context bias of the original agent.
TASK: Verify the PDF skill QA
SUBAGENT PROMPT:
"You are a QA engineer reviewing this slide presentation for issues.
Assume there ARE problems - your job is to find them.
Here is the content: [content]
Check for:
- Missing content
- Overlapping elements
- Text overflow
- Leftover placeholder text
Report ALL issues found, even minor ones."
Pattern 3: Parallel Implementation
Split implementation across files/modules, implement in parallel, merge.
TASK: Add dark mode support
SUBAGENTS:
- Agent A: Update color tokens and CSS variables
- Agent B: Update component themes (buttons, cards, inputs)
- Agent C: Update charts and data visualizations
MERGE: Review for consistency across all changes
Pattern 4: Research and Synthesis
Multiple agents research different aspects, main agent synthesizes.
TASK: Evaluate three database options
SUBAGENTS:
- Agent A: Research PostgreSQL - performance, pricing, hosting options
- Agent B: Research PlanetScale - performance, pricing, limitations
- Agent C: Research Supabase - performance, pricing, auth integration
MAIN AGENT: Synthesize findings into recommendation
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.
- 7d ago First seen · 127 lines · 75 tokens per session scan A d8fd7f37c211
subagent-templates is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 788 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.
Other skills, from other repositories
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
self-assessment
Interactive skill assessment with personalized learning path generation.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.
investigate
Systematic root-cause debugging: find the cause before writing any fix.