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/alphabravo-oss/guild/flow-interviewergit clone --depth 1 https://github.com/alphabravo-oss/guildWhat 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 | $0.00098 | $0.03448 |
| Opus 5 | $0.00049 | $0.01724 |
| Sonnet 5 | $0.00020 | $0.00690 |
| Haiku 4.5 | $0.00010 | $0.00345 |
Grade A, and why
flow-interviewer 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow-Interviewer — METHODOLOGY REFERENCE
This document describes the brownfield V3 R2 interview methodology. The main Claude thread follows this methodology directly — it does NOT spawn this document as a subagent. Subagent runtimes have no AskUserQuestion, so a spawned subagent cannot conduct the interactive node-by-node interview and silently falls back to forced decisions. The methodology must run in the main thread (the session that ran /forge:plan); see forge/commands/plan.md §R2 V3 override for the executable procedure.
Input: a flow-graph.json produced by flow-mapper and a natural-language feature request from the user. Output: flow-delta.json — an ordered list of new hops the user has confirmed, each grounded in the flow graph.
The methodology does NOT produce a traditional end-state spec. That shape is exactly what V3 is engineered to prevent. It produces a DAG of grounded hops.
Philosophy
The graph is the ground. The user locks the two anchors; you sketch the branches between them. The user gives you TWO confirmed points:
- The end state — described in the user's own words via the FEATURE_NAME /
--context FILEat invocation (or the 1-2 sentence clarification captured at the start of R2). - The entrypoint — the existing graph node where the new chain attaches, confirmed by the user via an explicit
AskUserQuestionin R2 step 3. You DO NOT guess the entrypoint; the user picks it from ranked candidates in the flow graph.
Your job is to sketch the hops between those two anchors. That is a constrained problem — not a two-endpoint guess. Every new hop attaches forward from the confirmed entrypoint and advances toward the end state. You do not invent either end.
Node-by-node beats big-bang. You propose one hop at a time. You wait for the user's confirmation before moving on. When the user rejects or adjusts a hop, you rework it before proposing the next. A hop is PINNED when the user says yes; later hops cannot change pinned ones.
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.
- yesterday First seen · 189 lines · 98 tokens per session scan A 934ac52df8fc
flow-interviewer is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 3,448 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…