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/willackerly/rebar/fanout_patterngit clone --depth 1 https://github.com/willackerly/rebarWhat 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 | $0.00000 | $0.02343 |
| Opus 5 | $0.00000 | $0.01171 |
| Sonnet 5 | $0.00000 | $0.00469 |
| Haiku 4.5 | $0.00000 | $0.00234 |
Grade A, and why
FANOUT_PATTERN 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fanout Pattern — Parallel Subagents Without Merge Conflicts
Status: active — load-bearing doctrine for multi-subagent fanout
Source: feedback/processed/2026-04-28-multi-subagent-fanout-playbook.md
Provenance: dapple-sdk, 2026-04-28 — two fanout cycles in one ~16hr
session, 9 fanned-out worktree branches, all merged with zero conflict
resolution; ~12–16 hours of sequential work landed in ~6–8 hours at the
same correctness bar.
Audience: the orchestrating (parent) agent. Subagents read
subagent-guidelines.md instead.
This document codifies the fanout shape so no project re-derives it — or wings it and merge-conflicts its way through. The deep mechanics live elsewhere and are referenced, not duplicated:
- Pre-launch audit, GC protection, agent health, recovery protocol —
practices/multi-agent-orchestration.md - Conflict zones, merge ordering, cherry-pick resolution —
practices/worktree-collaboration.md - Subagent behavioral contract (The 10 Rules, verify-before-relying) —
subagent-guidelines.md
The shape in one glance
Move 0 decide whether to fan out at all ← parent
Move 1 dependency graph + file-ownership table ← parent
Move 2 one worktree + one branch per chunk ← parent creates
Move 3 dispatch: allowlist + do-not-touch + ← parent prompts
verify-before-relying clause
(subagents work in parallel: verify brief,
work, commit to own branch — no push, no
branch switch, no main worktree)
Move 4 merge sequentially, --no-ff, test between ← parent
Move 5 post-merge sweep of shared surfaces, ← parent, one commit
then worktree prune
Every move that touches shared state belongs to the parent. Subagents own exactly their allowlisted files on exactly their own branch — nothing else. That division is why the merges are boring.
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 · 222 lines · 0 tokens per session scan A 9c05e57a1ca8
FANOUT_PATTERN is an agent published in the GitHub repository willackerly/rebar (5 stars, last pushed 20d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,343 tokens. 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.
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…
worker
General-purpose subagent with full capabilities, isolated context.