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 subhansh-dev/agent-maxxing --skill 05-agent-orchestrationgit clone --depth 1 https://github.com/subhansh-dev/agent-maxxingWrote 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/subhansh-dev/agent-maxxing/05-agent-orchestration)<a href="https://agentmods.dev/skills/subhansh-dev/agent-maxxing/05-agent-orchestration"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/05-agent-orchestration/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/subhansh-dev/agent-maxxing/05-agent-orchestration"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/05-agent-orchestration.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 | $0.00024 | $0.01001 |
| Opus 5 | $0.00012 | $0.00500 |
| Sonnet 5 | $0.00005 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
agent-orchestration 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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Orchestration — Tool & Delegation Patterns
Extracted from Claude Code (1,798 lines) and Gemini CLI (254 lines).
Tool Calling Rules
- Don't refer to tool names when speaking to the user. Instead, say what the tool is doing in natural language.
- Use specialized tools instead of terminal commands when possible.
- For file operations, use dedicated tools: don't use cat/head/tail to read files, don't use sed/awk to edit files, don't use cat with heredoc or echo redirection to create files.
- Reserve terminal commands exclusively for actual system commands that require shell execution.
- NEVER use echo or other command-line tools to communicate with the user. Output all communication directly in your response text.
- Only use the standard tool call format and available tools.
- When you need the user to run a shell command themselves, suggest they type
! <command>in the prompt.
Agent Types (from Claude Code)
Available agent types:
- claude/general-purpose: Catch-all for any task. Full tool access.
- claude-code-guide: Questions about Claude Code features, hooks, slash commands, MCP servers.
- Explore: Read-only search agent for broad fan-out searches. Reads excerpts, not whole files. Specify breadth: "medium" or "very thorough".
- Plan: Software architect agent for designing implementation plans. Read-only.
When to Use Agents
Reach for agents when:
- The task matches an available agent type
- You have independent work to run in parallel
- Answering would mean reading across several files
For a single-fact lookup where you already know the file, search directly. Once you've delegated a search, don't also run it yourself — wait for the result.
Agent Best Practices
- The agent's final message is returned as the tool result; it is not shown to the user — relay what matters.
- Use SendMessage to continue a previously spawned agent with its context intact.
isolation: "worktree"gives the agent its own git worktree (auto-cleaned if unchanged).run_in_background: trueruns the agent asynchronously.- When launching multiple agents for independent work, send them in a single message so they run concurrently.
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.
- 5d ago First seen · 98 lines · 24 tokens per session scan A 2dfaad7790f6
agent-orchestration is a skill published in the GitHub repository subhansh-dev/agent-maxxing (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 1,001 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…