Agent Workspace

Pack comparison

Two packs, side-by-side. Merged comparisons, shared shape, and diff highlights in one view.

ACommunityreferencev0.1.0Recommended
Nine Context Sources

nine-context-sources

CLAUDE.md is user context, not system prompt. 9 sources, 4 hierarchy levels, zero embeddings.

npx attrition-sh pack install nine-context-sources

Token budget

Pass rate

Avg tokens

Publisher

Agent Workspace

claude-codecursorcodex
BCommunityraghybridv0.1.0Recommended
Hybrid RAG: BM25 + Vector + Rerank

rag-hybrid-bm25-vector

Sparse + dense + cross-encoder. The 2025 retrieval default.

npx attrition-sh pack install rag-hybrid-bm25-vector

Token budget

8,000

Pass rate

Avg tokens

Publisher

Agent Workspace

claude-codecursorpython-3.11node-20

2 required outputs, 3 permissions, 4 completion conditions.

out: outputs/retrieval.json

What both packs have in common

Overlap across canonical pattern, compatibility, tags, and required packs.

claude-codecursor

Head-to-head claims from both packs

Each row is attributed to the pack that authored it. The winner column is normalised to this compare view (A / B / Tie).

SourceAlternativeAxisWinnerNote
Aclaude-code-guidemaintainabilityTieClaude Code Guide is the operator recipe (how to write AGENTS.md/CLAUDE.md); this pack is the architectural why (what CLAUDE.md is and is not). Use the guide to write the file, this pack to decide what belongs in it.
Arag-hybrid-bm25-vectorcomplexityAVector-DB RAG is the canonical retrieval pattern; Claude Code's file-based memory is the opposite bet (no embeddings, LLM scan of up to 5 file headers). Compare costs: vector adds index + latency + opacity; file-based is simple and auditable. Start with file-based; measure before adopting vector.
Aseven-safety-layersaccuracyAlternativeSafety layers are where enforcement lives deterministically; CLAUDE.md is where instruction lives probabilistically. For hard rules, safety-layers wins on accuracy because it actually blocks calls; this pack explains why CLAUDE.md can't.
Bpure-vector-ragaccuracyBHybrid+rerank beats pure vector by ~10–20% NDCG@10 on technical corpora with proper nouns and code symbols.
Bpure-vector-raglatencyAlternativePure vector is ~50ms faster — skip hybrid if latency budget is <80ms and accuracy is already acceptable.
Bpure-bm25accuracyBBM25 alone loses on paraphrase and conceptual queries. Hybrid adds ~15 points recall on natural-language question sets.
Bpure-bm25costAlternativeBM25-only has no embedding or rerank cost. Hybrid adds ~$0.001/query — negligible for most products but not all.

What each pack brings that the other doesn't

Unique coverage and any measurable gap between the two.

Comparisons not in B

claude-code-guiderag-hybrid-bm25-vectorseven-safety-layers

Compatibility A-only

codex

Tags A-only

referencecontextclaude-mdmemoryclaude-code-internalsdive-into-claude-code

Comparisons not in A

pure-vector-ragpure-vector-ragpure-bm25pure-bm25

Compatibility B-only

python-3.11node-20

Tags B-only

ragretrievalbm25vector-searchrerankinghybridcitations