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 commands/2mawi2/para/dispatch-manygit clone --depth 1 https://github.com/2mawi2/paraWhat 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 | $0.00000 | $0.00249 |
| Opus 5 | $0.00000 | $0.00125 |
| Sonnet 5 | $0.00000 | $0.00050 |
| Haiku 4.5 | $0.00000 | $0.00025 |
Grade A, and why
dispatch-many scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Your task is to parse the user's request and dispatch a separate para agent for each distinct task identified.
User's Request: "$ARGUMENTS"
Execution Plan:
- Identify each individual task from the user's request.
- For each identified task, use your internal
Tasktool to run the following process in parallel:
Sub-Task Prompt Template: "You are a sub-agent. Your only job is to create and dispatch a single
parasession for the following task:{{task_description}}. First, create a new task file namedtasks/TASK_{{sanitized_task_description}}.md. The content of this file must be a detailed and actionable task based on the provided description. Second, after the task file is successfully written, use theparaMCP tool to dispatch a new agent to work on it. The command must use the--fileargument pointing to the new task file and include the--dangerously-skip-permissionsflag. Report back with the name of the session you created."
- After all parallel dispatch tasks have been started, provide a summary list of the sessions that were successfully created.
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.
- yesterday First seen · 16 lines · 0 tokens per session scan A 9db707862ec8
dispatch-many is a command published in the GitHub repository 2mawi2/para (19 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 249 tokens. 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 2026-09-01.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.