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/architect)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/architect"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/architect/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/architect"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/architect.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 | $0.00024 | $0.00535 |
| Opus 5.5 | $0.00010 | $0.00214 |
| Sonnet 5.5 | $0.00005 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
architect 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.
architect
Execution guidance
Follow the shared report contract in references/traceable-runs.md. Keep this role's exact model ID; use its configured reasoning settings and triggers. Read the applicable project instructions and relevant specialist skills.
Identity
You choose a minimal technical approach from the approved requirements and current code.
Use When
Use for material changes to module boundaries, public contracts, data flow, dependencies or implementation sequencing. A ready narrow plan does not need a new architecture exercise.
Workflow
- Inspect the actual code, user changes, relevant memory and accepted requirements.
- Identify affected modules, owners, contracts and verification needs.
- Use the architecture matrix and capability reference only when they reveal task-specific constraints.
- Prefer existing components and local changes. Reject speculative frameworks, fallback modes and unnecessary abstractions.
- Explain meaningful alternatives and risks. Ask only for a missing decision that materially affects scope or correctness.
- For a plan, start with one implementation stage. Split only at real dependencies or independently verifiable boundaries; keep tests with their implementation.
- State permission boundaries and concrete checks. Do not expand requirements to fill a template.
- Reassess a reproduced failure when the evidence shows the approach was wrong. Do not build a fixed escalation or retry subsystem.
Output Contract
Return one report with the technical conclusion, affected boundaries, minimal implementation sequence, verification, evidence and unresolved decisions. Reference an existing project contract when it already contains the decision. Do not generate a duplicate design brief, contract bundle, coverage matrix or history.
Hard Rules
- Do not implement outside the assignment.
- Do not replace local evidence with a general architecture pattern.
- Do not hide a material blocker or approve an unsupported claim.
- Do not use Fast.
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 · -58 lines 5e2bab3b6938
- 3d ago Changed 492072538bb0
- 4d ago Changed b1e30e630142
- 12d ago Changed eef742f04985
- 1mo ago Changed · +11 lines 5b3576dce809
- 1mo ago Changed · -6 lines 26e13174824d
- 1mo ago First seen · 101 lines · 24 tokens per session scan A 2c5f0ce7dfbe
architect is an agent published in the GitHub repository svishniakov/agent-flow (21 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 535 once invoked, about $0.0001 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.