Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/1broseidon/oneagentnpx agentmods add skills/1broseidon/oneagent/oa-dispatchWrote 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/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/1broseidon/oneagent/oa-dispatch"><img src="https://agentmods.dev/badge/skills/1broseidon/oneagent/oa-dispatch.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 | $0.00058 | $0.01677 |
| Opus 5.5 | $0.00023 | $0.00671 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 6mo ago), licensed MIT. It adds 58 tokens to every session and 1,677 once invoked, about $0.0002 per session on Opus 5.5. 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
bigquery-graph
Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. Includes path finding, multi-hop traversal, topological connection, shortest path, node reachability, edge connectivity, and semantic graph queries.
adk-sample-creator
Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use. Use when the user wants to add a sample or example demonstrating a feature or agent pattern (dynamic nodes, fan-out/fan-in, a standalone…
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.