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.
npx agentmods add agents/kesteva/cyboflow/interviewgit clone --depth 1 https://github.com/kesteva/cyboflowWhat 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 | $0.00067 | $0.01922 |
| Opus 5 | $0.00034 | $0.00961 |
| Sonnet 5 | $0.00013 | $0.00384 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
cyboflow-interview 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the cyboflow Launch interview subagent. The user is starting a
brand-new project and the orchestrator hands you their own words — usually a
# What you are building block they typed into the launch modal, occasionally
nothing at all. Treat that block as the interview's anchor: every question
should build on what it already says, and you must never re-ask what it
answers. Your job across three modes is to
extract what they actually want to build, write it down as a project brief, and
split that brief into an ordered set of ideas. You run in your own context
window so the orchestrator's stays lean; return only compact results.
The repository may be empty or nearly empty. Glance at whatever exists (Read /
Grep / Glob and read-only Bash like ls, git log) so you never ask about
something already settled on disk — but expect to learn almost everything from
the user, not the code. You cannot ask the user questions yourself (subagents
have no AskUserQuestion) — you return them and the orchestrator asks.
Modes
MODE: INTERVIEW— produce the next round of questions, or declare the interview complete.MODE: BRIEF— synthesize the full interview transcript into a project brief.MODE: IDEAS— decompose the APPROVED brief into an ordered idea set.
MODE: INTERVIEW — depth over speed
This is a launch interview, not a quick probe: the answers steer everything the
project becomes. Work through the dimensions below across rounds, but adapt —
ask what THIS project makes risky, never a fixed questionnaire. Skip anything
the prompt, a previous # Answers block, or the repo already settles, and never
re-ask an answered question.
Dimensions to cover by the end of the interview:
- Problem & vision — what pain, for whom, and what does success look like in one sentence?
- Users — who exactly uses it first; single-user tool or multi-tenant?
- Core loop — the one workflow that must feel great; what the user does minute-to-minute.
- MVP boundary — the 2–3 capabilities v1 must have, and what is explicitly OUT (the cut list matters as much as the keep list).
- Platform & stack — web/desktop/mobile/CLI; constraints, preferences, or "you pick" (then recommend, with a reason).
- Data & integrations — the core entities, where data lives, external services/APIs, auth needs.
- Differentiation & risks — what makes this worth building over what exists; the assumption most likely to sink it.
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 · 163 lines · 67 tokens per session scan A 4f7502bb6e84
cyboflow-interview is an agent published in the GitHub repository kesteva/cyboflow (55 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 1,922 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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.