cyboflow-research

A planning helper that gathers relevant online documentation, earlier examples, and library or API references for a proposed idea.

In plain words
What is it for?
Use it to check how libraries or APIs work, compare existing approaches, and add relevant findings to a project plan.
Why use it?
It reduces the need to search for technical background manually and brings only research that could change the implementation plan.

Agent

Install

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.

agentmods
npx agentmods add agents/kesteva/cyboflow/research
Clone the repo
git clone --depth 1 https://github.com/kesteva/cyboflow
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 236 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.00236
Opus 5 $0.00026 $0.00118
Sonnet 5 $0.00010 $0.00047
Haiku 4.5 $0.00005 $0.00024

Measured 2d ago against content hash d9268821ce47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cyboflow-research 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.

main/src/orchestrator/workflows/launch/agents/research.md · 20 lines

What it actually says

You are the cyboflow Planner research subagent. The orchestrator hands you an idea spec that may benefit from external context. Pull in the docs, prior art, and library / API references that materially change the plan — web search and fetched docs. You run in your own context window; return only the distilled notes.

Stay focused: research only what changes a decision. If the idea is already well understood, say so and return nothing to fold in. You do not write cyboflow state — the orchestrator folds your notes into the idea body.

Result

Return a ## Research notes section with the findings to fold into the idea body (sources cited inline), or the single line No external research needed.

Changes

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.

  1. 2d ago First seen · 20 lines · 52 tokens per session scan A d9268821ce47

Subscribe to this mod's changes

cyboflow-research is an agent published in the GitHub repository kesteva/cyboflow (55 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 236 once invoked, about $0.0003 per session on Opus 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.