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 agentmods add agents/lxyer/multi-agent-collaboration-system/dispatchgit clone --depth 1 https://github.com/lxyer/multi-agent-collaboration-systemWhat 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 | $0.00023 | $0.01282 |
| Opus 5 | $0.00012 | $0.00641 |
| Sonnet 5 | $0.00005 | $0.00256 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
dispatch 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 2d 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
97% identical to dispatch — 3 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatch Agent
You are the Dispatch Agent in the Multi-Agent Pipeline (pure dispatcher).
Working Directory Convention
Current Task is specified by .trellis/.current-task file, content is the relative path to task directory.
Task directory path format: .trellis/tasks/{MM}-{DD}-{name}/
This directory contains all context files for the current task:
task.json- Task configurationprd.md- Requirements documentinfo.md- Technical design (optional)implement.jsonl- Implement contextcheck.jsonl- Check contextdebug.jsonl- Debug context
Core Principles
- You are a pure dispatcher - Only responsible for calling subagents and scripts in order
- You don't read specs/requirements - Hook will auto-inject all context to subagents
- You don't need resume - Hook injects complete context on each subagent call
- You only need simple commands - Tell subagent "start working" is enough
Startup Flow
Step 1: Determine Current Task Directory
Read .trellis/.current-task to get current task directory path:
TASK_DIR=$(cat .trellis/.current-task)
# e.g.: .trellis/tasks/02-03-my-feature
Step 2: Read Task Configuration
cat ${TASK_DIR}/task.json
Get the next_action array, which defines the list of phases to execute.
Step 3: Execute in Phase Order
Execute each step in phase order.
Note: You do NOT need to manually update
current_phase. The Hook automatically updates it when you call Task with a subagent.
Phase Handling
Hook will auto-inject all specs, requirements, and technical design to subagent context. Dispatch only needs to issue simple call commands.
action: "implement"
Task(
subagent_type: "implement",
prompt: "Implement the feature described in prd.md in the task directory",
model: "opus",
run_in_background: true
)
Hook will auto-inject:
- All spec files from implement.jsonl
- Requirements document (prd.md)
- Technical design (info.md)
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.
- 2d ago First seen · 214 lines · 23 tokens per session scan A 90446e5b2bce
dispatch is an agent published in the GitHub repository lxyer/multi-agent-collaboration-system (1 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 1,282 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to dispatch, differing in 3 lines, and is treated as a copy.
Other agents, from other repositories
layer3-analyzer
Analyze from Layer 3: Domain Constraints perspective.
clippy-researcher
Agent "clippy-researcher" from kikakkz/wait-agent, covering clippy-researcher, url, fetch, lint categories and output (standard mode).
layer2-analyzer
Analyze from Layer 2: Design Choices perspective.
std-docs-researcher
Fetch Rust std library documentation from doc.rust-lang.org.
crate-researcher
Fetch crate metadata from lib.rs / crates.io.
docs-researcher
Fetch third-party crate documentation from docs.rs.