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 skills/1broseidon/oneagent/oa-dispatchnpx skills add 1broseidon/oneagent --skill oa-dispatchgit clone --depth 1 https://github.com/1broseidon/oneagentWrote 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/1broseidon/oneagent/oa-dispatch)<a href="https://agentmods.dev/skills/1broseidon/oneagent/oa-dispatch"><img src="https://agentmods.dev/badge/skills/1broseidon/oneagent/oa-dispatch.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 | $0.00058 | $0.01677 |
| Opus 5 | $0.00029 | $0.00839 |
| Sonnet 5 | $0.00012 | $0.00335 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
oa-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 4d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatch Tasks to Other Agents
Use oa to delegate scoped coding tasks to a different AI model or backend. This is useful when you want to parallelize work, use a specific model's strengths, or offload a well-defined edit while you continue working.
When to dispatch
Dispatch works best for targeted, self-contained tasks with clear instructions:
- Edit a specific file or function
- Generate a test suite for a module
- Refactor a block of code to match a pattern
- Review a file for a specific concern (security, performance, etc.)
Do not dispatch vague or open-ended tasks. The receiving agent has no access to your conversation context — the prompt must be self-contained.
Basic command
Always pipe the prompt into oa instead of passing it as an argument. This keeps prompt content out of process listings (ps aux):
echo "<prompt>" | oa -b <backend> -m <model> --thinking <level>
All flags are optional. --thinking controls reasoning effort — supported levels vary by backend (e.g. low, medium, high). Omit it to use the backend's default.
For background execution with streaming visibility:
echo "Edit path/to/file.go: <specific instructions>" | oa -b claude --jsonl
For multi-line prompts, use a heredoc:
cat <<'EOF' | oa -b codex --jsonl
Edit internal/auth/handler.go: add rate limiting to the Login function.
Use x/time/rate with a limit of 5 requests per second per IP.
Do not modify any other functions. Do not ask for confirmation, just make the edits.
Run go test ./internal/auth/... when done.
EOF
Constructing effective prompts
The prompt must include everything the agent needs. Always include:
- The file path to edit or read
- What to do — be specific about the change
- Constraints — what not to change, patterns to follow, tests to pass
Good prompt:
Edit internal/auth/handler.go: Add rate limiting to the Login function.
Use x/time/rate with a limit of 5 requests per second per IP.
Do not modify any other functions. Do not ask for confirmation, just make the edits.
Run go test ./internal/auth/... when done.
What ships with it
2 files 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.
- 4d ago First seen · 170 lines · 58 tokens per session scan A 187b1bbfcaef
oa-dispatch is a skill published in the GitHub repository 1broseidon/oneagent (5 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 1,677 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
normal-skill
A normal skill with a hyphen.
underscore-skill
A skill with an underscore.
root-skill
root skill.
a-b
conflicting skill 2.
coordinate-agents
Route Codex-native multi-agent orchestration in a Git repository through a local-first, recoverable Agent Bus. Use for role-based planning, task execution, review, recovery, adapters, and human-gated release workflows. The plugin supports Codex CLI, Google Antigravity CLI, Claude, and other configured coding agents.…
coordinate-task
Run a Coordinate Agents Task from requirement clarification through planning, implementation, review, and the human release gate. Hide Agent Bus transport details behind the durable Task API.