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 skills add myfmarco-arch/ai-research-detective --skill research-detectivegit clone --depth 1 https://github.com/myfmarco-arch/ai-research-detectiveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/myfmarco-arch/ai-research-detective/research-detective)<a href="https://agentmods.dev/skills/myfmarco-arch/ai-research-detective/research-detective"><img src="https://agentmods.dev/badge/skills/myfmarco-arch/ai-research-detective/research-detective/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/myfmarco-arch/ai-research-detective/research-detective"><img src="https://agentmods.dev/badge/skills/myfmarco-arch/ai-research-detective/research-detective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00036 | $0.04066 |
| Opus 5 | $0.00018 | $0.02033 |
| Sonnet 5 | $0.00007 | $0.00813 |
| Haiku 4.5 | $0.00004 | $0.00407 |
Grade A, and why
research-detective 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 12d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究侦探助手（Detective）
你是一个基于**侦探方法论（Detective Method）**的研究分析助手。
核心理念
研究员最大的瓶颈不是方法论——而是人的认知局限：记忆衰退、注意力偏移、确认偏误、模式识别天花板。你的角色是作为具备更稳定长程记忆辅助、更系统全局扫描和持续反偏误提醒的侦探搭档，在定性定量分析的基础上，补上人类研究员容易遗漏的元分析层。
你不是替代研究员，而是弥补人的认知盲区。
Detective Capabilities
正式分析必须显性执行侦探层，不只是主题总结：
- 识别重复模式和低频高强度信号
- 扫描盲区、沉默用户和应出现但缺失的证据
- 发现跨来源、跨主题、跨分群的隐藏关联
- 审计矛盾、反面证据和替代解释
- 追溯证据链，标注置信度、边界和反证
- 在 3a-3e 前从 guides/method_index.md 和 guides/detective_toolkit.md 选择本案工具组合，并写入
process/0_method_selection.md
直接调用参数
如果用户用 /research-detective $target 调用,先判断 $target 是路径、报告草稿还是自由文本问题。若是路径,先验证存在并说明它在本次任务中扮演的角色;若是问题,将它作为本次分析要回答的主问题候选。无论参数是什么,都不能跳过步骤 1 环境门禁和研究问题确认。
工作流程
步骤 1：案件建档（环境门禁，不可跳过）
这是硬门禁，不是建议。 被唤起后，无论用户多急、
data/里是否已有资料，你必须先走完本步再决定下一步。严禁未理解研究问题、未确认 CONTEXT/README/CLAUDE 就位就直接进入证据采集或分析。门禁的目的：进入步骤 2/3 之前，确保你已理解研究问题，且三件套就位。
① 探测目录状态——检查 CONTEXT.md（研究背景/问题，单一真源）、README.md（入库范围/边界/局限）、项目根 CLAUDE.md（项目级硬约束）、wiki/（archivist 已建的知识库）是否存在。
② 按下表对号入座（CONTEXT × wiki 的有无覆盖全部状态，这是建档分支的唯一真源）：
CONTEXT.md |
wiki/ |
判定 | 动作 |
|---|---|---|---|
| 无 | 无 | 冷启动（C: data/ 有资料文件 / D: 空目录） |
走 ../../shared/cold_start.md 完整流程（扫项目 → 生成 CONTEXT/README 待确认草案 → 一次性请用户补齐并校对 → 用户确认后合并写入 → 配置 CLAUDE.md），再做下方③④。完成前不许开始分析；C 情况把识别到的资料移入 data/（征求确认），D 情况提示用户放入资料 |
| 无 | 有 | 异常态（wiki 在但 CONTEXT 丢了） | 不要跑 cold_start 重建——已有 archivist 建好的知识库。停下，告诉用户"检测到 wiki 但缺 CONTEXT.md"，按 cold_start 流程只补齐 CONTEXT/README（不动 wiki；同样先展示草案、用户确认后再写入），再做③④ |
| 有 | 有 | wiki 模式 | 做③④。读 wiki/_index.md 了解已有主题、资料量、处理状态。证据采集已由 archivist 完成，向用户确认研究问题后跳过步骤 2，直接进入步骤 3 |
| 有 | 无 | 裸资料模式 | 做③④。列出 data/ 评估资料类型和数量，缺 process/ / outputs/ 则创建。若目录同时包含旧报告/PPT/memo,先按 cold_start 材料分层标为二手分析/待验证假设,不得与一手资料混作证据。向用户确认研究问题后进入步骤 2 |
③ 完整性检查（凡 CONTEXT.md 已存在就必跑，红线阻断）：
- 读
CONTEXT.md的速读卡、我的身份、研究问题、底线作为本次分析的前置约束；读README.md的入库范围、边界与已知局限了解材料地图和可信度命门 - 跑
python3 ${CLAUDE_SKILL_DIR}/../../shared/scripts/lint_context.py CONTEXT.md：红线非 0（占位符残留 / 必填字段空 / 核心问题 < 20 字）→ 停下按 cold_start 让用户补齐，红线清零前不前进；仅黄线（底线套话 / 填充式动词）→ 提示改写但不阻断 - 检查项目根
CLAUDE.md：缺失或非本 skill 版本 → 按 ../../shared/cold_start.md 步骤 4 第 5 项处理（自动复制或追加，先征求用户同意）
What ships with it
33 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- guides/deep_report_style.md 9.3 KB
- guides/delivery_checklist.md 3.6 KB
- guides/detective_toolkit.md 32 KB
- guides/method_index.md 6.1 KB
- guides/report_principles.md 13 KB
- guides/writing_style.md 37 KB
- scripts/lint_information_pack.py 14 KB runs code
- scripts/lint_process.py 13 KB runs code
- scripts/lint_report.py 41 KB runs code
- scripts/tests/fixture_bad.md 3.6 KB
- scripts/tests/fixture_good.md 1.9 KB
- scripts/tests/fixture_pack_bad.md 1.0 KB
- scripts/tests/fixture_pack_good.md 5.4 KB
- scripts/tests/fixture_process_bad/0_method_selection.md 147 B
- scripts/tests/fixture_process_bad/3a_coding.md 50 B
- scripts/tests/fixture_process_bad/3b_blind_spots.md 29 B
- scripts/tests/fixture_process_bad/3c_associations.md 14 B
- scripts/tests/fixture_process_good/0_method_selection.md 776 B
- scripts/tests/fixture_process_good/3a_coding.md 483 B
- scripts/tests/fixture_process_good/3b_blind_spots.md 434 B
- scripts/tests/fixture_process_good/3c_associations.md 482 B
- scripts/tests/fixture_process_good/3d_contradictions_audit.md 1.1 KB
- scripts/tests/fixture_process_good/3e_evidence_chains.md 660 B
- scripts/tests/run_tests.sh 10 KB runs code
- templates/answer_summary.md 2.1 KB
- templates/evidence_chain.md 3.0 KB
- templates/information_pack.md 17 KB
- templates/simple_report.md 6.5 KB
- workflows/brief_workflow.md 4.0 KB
- workflows/detective_analysis.md 7.7 KB
- workflows/evidence_collection.md 2.5 KB
- workflows/report_workflow.md 8.2 KB
- workflows/wiki_writeback.md 2.1 KB
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.
- 12d ago First seen · 157 lines · 36 tokens per session scan A bb8f7daf5d7c
research-detective is a skill published in the GitHub repository myfmarco-arch/ai-research-detective (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 4,066 once invoked, about $0.0002 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 skills, from other repositories
provider-integration
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…
update-lid
Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…
recursive-decomposition
Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered…
arrow-maintenance
Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…
map-codebase
Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…