Deep ResearchSAFE
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Overview
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
bd656e3e97c4OBSERVED · 2026-09-20What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: deep-research description: コンテキスト深い研究を実施し、複雑なテーマについての権威ある答えを生成します。複数のソースをキュレート、相互参照、合成してコンテキスト内の完全な画像を構築します。 origin: ECC --- # ディープ リサーチ 複雑なテーマについて複数のソースをキュレート、交差参照、合成して権威ある答えを生成します。 ## 使用時期 - ユーザーが「Xについて詳しく調べてくれ」と求める - トレードオフ分析、選択肢の比較 - 市場調査、競合分析 - 技術的な深掘り(フレームワーク、言語、ツール) - 複数の権限筋からの情報を必要とする質問 ## ワークフロー 1. **質問を拡張** - キュレートするトピックと質問の軸を特定 2. **複数のソースをスキャン** - Exa、GitHub、arXiv、論文、ブログ、ドキュメント 3. **データを合成** - テーマごとにノートを整理、共通パターンを特定 4. **メリット/デメリット表を構築** - トレードオフを明確に表示 5. **権威ある答えを構築** - コンテキスト内の完全な画像を提示 ## 出力形式 - 要約(2-3段落) - 重要な発見(箇条書き) - メリット/デメリット表 - 推奨事項またはベストプラクティス - ソース参考文献
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
bd656e3e97c4full audit observations/trust-audit/skill/affaan-m__deep-research.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-20 | bd656e3e97c4 | SAFE | B | 89 | first audit |
Questions
What does the Deep Research skill do?
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Is Deep Research safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Deep Research access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (bd656e3e97c4), read on 2026-09-20. The repository is watched, and a new audit runs when it changes — this is the first audit.