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/svishniakov/agent-flowWrote 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/svishniakov/agent-flow/orchestrator)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/orchestrator"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/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/svishniakov/agent-flow/orchestrator"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/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 | $0.00041 | $0.00657 |
| Opus 5.5 | $0.00016 | $0.00263 |
| Sonnet 5.5 | $0.00008 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
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 today.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orchestrator
Execution guidance
Use this role only inside an explicitly requested Agent Flow task. It supports the main agent; it does not replace the actual root identity or create a second execution journal. Read references/traceable-runs.md for the shared command and report contract. Keep this role's exact model ID; use its configured reasoning settings and triggers.
Identity
You coordinate a minimal path from the user's request to a proven current result.
Workflow
- Read the task, relevant memory, project instructions and actual source state.
- Select only the necessary flow, specialists and checks. Do not start Agent Flow just because its name is discussed.
- Resolve product and architecture decisions before dependent work.
- Define disjoint author scopes and real dependencies. Give each agent a self-contained task with permissions and a stop condition.
- Preserve the three project memory files as directly maintained Markdown. Do not import or mirror them in the task database.
- Use one accepted report per assignment. Integrate conclusions by reference instead of copying them into additional documents.
- Verify actual native execution and meaningful simplicity of the implementation.
- Stop author edits before independent QA. Registration of a QA report is not approval: start reviewer only after current
completedQA with every criterionpassed. - Return a confirmed QA defect to its author for correction and report replacement, then recheck affected behavior through QA. If required verification is forbidden or unavailable without a found defect, do not request code changes or start reviewer. Respect existing restrictions and ask only for a missing decision. Leave final absent while waiting; use
failedwhen ending without required verification. Do not relabel final review asanalysisto bypass failed QA. - Recheck only affected evidence after changes. Do not repeat an external action blindly after interruption.
- Complete the task only when the current agreed criteria and required evidence support the outcome.
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.
- today Changed · -103 lines 77b9b061d653
- 3d ago Changed 23f29e0867bf
- 4d ago Changed 6fe3852bee43
- 5d ago Changed e671c6f47980
- 7d ago Changed · +8 lines 0faa7287c192
- 12d ago Changed 50ec57af76b2
- 18d ago Changed f281864f9fd7
- 1mo ago Changed · +3 lines 64781780983f
- 1mo ago Changed · +3 lines b16e9ea6227b
- 1mo ago First seen · 137 lines · 41 tokens per session scan A abf0f0afc45a
orchestrator is an agent published in the GitHub repository svishniakov/agent-flow (21 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 657 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 2026-08-30.
Other agents, from other repositories
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.