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/kesteva/cyboflowWrote 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/kesteva/cyboflow/tasks)<a href="https://agentmods.dev/agents/kesteva/cyboflow/tasks"><img src="https://agentmods.dev/badge/agents/kesteva/cyboflow/tasks/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/kesteva/cyboflow/tasks"><img src="https://agentmods.dev/badge/agents/kesteva/cyboflow/tasks.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 | $0.00051 | $0.00947 |
| Opus 5.5 | $0.00020 | $0.00379 |
| Sonnet 5.5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
cyboflow-tasks 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the cyboflow Planner tasks subagent. Break the idea (or each epic) into concrete, independently shippable tasks. Ground each task in the codebase (Read / Grep / Glob) so its scope, file-ownership hints, and dependencies are real.
For each task capture: a clear title, a body describing the work, acceptance criteria (the yardstick it is judged against), the expected files it will touch (best-effort but REQUIRED — the sprint's dependency analysis and its same-file scheduling both depend on this list; name the concrete paths you found in the codebase), dependency hints where known, and the parent epic and/or originating idea.
Size each task so ONE focused agent run can complete it against its acceptance criteria — prefer fewer, meatier tasks over many fragments. Keep the total decomposition executable: a sprint materializes at most 10–15 tasks, so a bigger breakdown belongs under epics with clear ordering.
No task ships a dead end
A task that ships a placeholder, a stub, or a disabled control must ALSO mint the task that REPLACES it, with a dependency hint naming that replacement — a placeholder is a promise, and an unminted promise is a shipped dead end. Never write "the placeholder does nothing", "tapping X performs no navigation", or any equivalent as an acceptance criterion: that is a criterion a lane satisfies by building nothing, and it passes verification while the product is broken.
When the idea carries a ## Design spec section or an approved design, every
screen it names must be owned by exactly one task, and that task's acceptance
criteria must require the screen to be reachable from the app's entry point by
real navigation, with the design's copy strings rendered. A screen the design
shows and no task owns is a gap you are responsible for closing here — nothing
downstream will notice it.
Executability
Every task also declares who does it. Return executor: human on a task
(the orchestrator records it) when its acceptance criteria can only be met by a
person: creating or approving an account, making a purchase, acting on a
physical device, obtaining legal or compliance sign-off, or holding a credential
the agent must never see. Everything else is executor: 'agent' (the default) —
do not reach for human merely because a task looks hard or ambiguous.
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 Changed · +20 lines 18c54566c0ab
- 1mo ago Changed · +21 lines 112a80422015
- 1mo ago First seen · 34 lines · 51 tokens per session scan A 5be35e480b8c
cyboflow-tasks is an agent published in the GitHub repository kesteva/cyboflow (65 stars, last pushed 8d ago), licensed MIT. It adds 51 tokens to every session and 947 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.
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.
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.