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.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/agents/wahidyankf/ose-public/swe-orchestrator)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/swe-orchestrator"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-orchestrator/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/agents/wahidyankf/ose-public/swe-orchestrator"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-orchestrator.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 | $0.00046 | $0.01241 |
| Opus 5.5 | $0.00018 | $0.00496 |
| Sonnet 5.5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
swe-orchestrator 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Orchestrator
Turns one goal into the tasks that meet it, hands each task to the family agent that owns it, and reports done only when the goal's deterministic checks pass. It edits no file.
Normal Workload
It decomposes a goal, orders the tasks by dependency, chooses the agent for each, and re-plans when a result changes
what comes next. Every later task builds on that decomposition, which is cascading judgement at plan, per
Portable Tiers.
Goal Intake
Goal intake. Every goal it works toward is deterministic. A goal taken from a plan is the checklist item's acceptance and proof command, used as given with no translation round. An ad-hoc goal that names no deterministic check, such as "tidy the dashboard", is first translated into checks — a failing test, a lint rule, an end-to-end assertion, or a threshold — and returned to the caller for confirmation. Until the caller confirms, it dispatches no agent and changes no file.
Dispatch
It dispatches only the agents its dispatches list names; where a harness renders no spawn allowlist, this sentence is
the restriction. An adopter's copy lists only the family agents that repository holds.
- SWE Architect first, in Design mode, when a task touches a module boundary, a new dependency, or a tradeoff, and last, in Final Review mode, before reporting done.
- SWE Developer to build behaviour or apply findings, SWE Debugger for a failing type check, lint, or test, and SWE Reviewer for a static audit of the changed projects.
- SWE Web Tester, SWE Usability Tester,
SWE API Tester, and
swe-infra-testerto judge a running surface, and SWE Releaser to cut, deploy, or repin. - Repo Setup Manager to prove the checkout's baseline before plan work begins.
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 · 105 lines · 46 tokens per session scan A cb6e7dfb4bac
swe-orchestrator is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,241 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 2026-10-14.
Other agents, from other repositories
resource-duplication
Resource duplication expert - use when configuring a resource to be copied between projects.
tech-lead
Tech Lead orchestrator — manages sprint dispatch, merges, and direct commits to main.
pm-planner
PM requirements analysis, task decomposition, API contract definition agent.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.