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 Mark-Libetter/ai-conversation-hub --skill find-agent-datagit clone --depth 1 https://github.com/Mark-Libetter/ai-conversation-hubWrote 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/mark-libetter/ai-conversation-hub/find-agent-data)<a href="https://agentmods.dev/skills/mark-libetter/ai-conversation-hub/find-agent-data"><img src="https://agentmods.dev/badge/skills/mark-libetter/ai-conversation-hub/find-agent-data/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/mark-libetter/ai-conversation-hub/find-agent-data"><img src="https://agentmods.dev/badge/skills/mark-libetter/ai-conversation-hub/find-agent-data.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 | $0.00145 | $0.01653 |
| Opus 5 | $0.00072 | $0.00826 |
| Sonnet 5 | $0.00029 | $0.00331 |
| Haiku 4.5 | $0.00015 | $0.00165 |
Grade A, and why
find-agent-data 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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Agent Data
把本 skill 当作“本地 AI 会话发现与恢复层”，不是单纯的路径清单。Qoder/QoderCN 与 Grok Build 的映射实现只放在 agent_recovery/，对话中心适配器复用同一份代码。目标是输出可验证的链路：
产品 → 索引 → 正文候选 → 覆盖率选择 → 来源证据 → 局限
不可违反的约束
- 先查默认路径和官方环境变量；不要从磁盘根目录递归扫描。
- 默认只读。SQLite 使用
mode=ro和PRAGMA query_only=ON。 - 不读取或导出
auth.json、openclaw.json、token、Cookie、API key 等凭据。 - 不破解或解密厂商字段。加密正文只能标记为不可直接读取，再寻找明文 transcript。
- “目录存在”不等于“已找到对话”。只有会话表、消息表或 transcript 才算对话证据。
- 区分
verified、partial与未知，不把推测写成事实。 - 读正文时保存文件路径、行号、事件 ID（若有）和内容行哈希；摘要不能替代来源证据。
工作流
1. 先做发现
运行：
python scripts/find_agent_data.py --existing-only --probe --json
只查某个产品：
python scripts/find_agent_data.py qoder --probe --json
python scripts/find_agent_data.py grok --probe --json
发现结果使用 find-agent-data/v2 JSON。检查：
detected是否由conversation_evidence=true的位置触发；confidence是verified还是partial；- SQLite 是否可只读打开、当前有哪些表；
warnings是否提示凭据目录、加密字段或覆盖不完整。
若用户只问“数据在哪里”，到此即可。不要顺带读取对话正文。
2. 需要找具体对话时，先索引后正文
按以下顺序：
- 用标题、session ID、项目名和更新时间在索引层缩小范围。
- 把索引 ID 映射到所有已知正文候选，不能命中第一个就停止。
- 安全解析每个候选中的 user/assistant 消息。
- 以有效消息数为主、末条证据行和修改时间为辅，选覆盖最完整的候选。
- 报告未命中的索引会话为
metadata_only，不能说“完整回顾成功”。
通用证据模型和报告格式见 references/recovery-sop.md。产品路径与 schema 线索见 references/agent-storage.md。
3. Qoder/QoderCN 使用专用映射探针
按标题查找且默认不显示正文：
python scripts/qoder_session_probe.py --product qoder --query "继续codex项目优化" --json
需要回顾卡片时，显式增加 --preview：
python scripts/qoder_session_probe.py --product qoder --query "继续codex项目优化" --preview --json
探针只读 chat_session 的安全元数据，不读 chat_message.content。它会同时检查：
- 完整会话 ID 对应的 full transcript；
- 6–24 字符任务 ID 前缀对应的 compact transcript；
- 所有候选的有效消息数、首末证据行、事件 ID 和行哈希。
若 chat_session 有标题但找不到明文候选，报告 metadata_only。若给出精确 session ID，即使索引已丢失，也可尝试从 transcript 根恢复。
4. Grok Build 使用专用映射探针
按标题查找且默认不显示正文：
python scripts/grok_session_probe.py --query "对话中心" --json
What ships with it
11 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.
- agent_recovery/__init__.py 666 B runs code
- agent_recovery/common.py 7.3 KB runs code
- agent_recovery/grok.py 14 KB runs code
- agent_recovery/qoder.py 23 KB runs code
- agents/openai.yaml 275 B
- references/agent-storage.md 6.2 KB
- references/recovery-sop.md 5.4 KB
- scripts/find_agent_data.py 13 KB runs code
- scripts/grok_session_probe.py 3.1 KB runs code
- scripts/qoder_session_probe.py 3.6 KB runs code
- tests/test_scripts.py 12 KB runs code
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.
- 9d ago First seen · 134 lines · 145 tokens per session scan A cf782734a0be
find-agent-data is a skill published in the GitHub repository Mark-Libetter/ai-conversation-hub (3 stars, last pushed 19d ago), licensed MIT. It adds 145 tokens to every session and 1,653 once invoked, about $0.0007 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
cao-learning
Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learningenabled; degrade silently when the tools…
cao-memory
Store, recall, and forget durable facts with CAO memory — user preferences, project conventions, decisions, and corrections that should persist across sessions and agents. Use proactively to check memory before asking the user, and to save anything worth remembering. Distinct from any provider-native memory.
lore
SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence, and interactively forge the chosen ones into skills installed across all your agent harnesses. Use when the user…
lov-auto-context
Manual or hook-triggered context operator. Evaluates the current session for pollution (long conversations, topic drift, stale noise), AND takes concrete context-shaping actions: writing project memory, updating global or project CLAUDE.md (with diff + confirm), and recommending harness commands like /fork, /compact…
lov-ataru-indexing
A maintenance tool for building, repairing, or checking a local searchable index of Ataru AI conversation history. An index is an organised lookup structure that makes searching stored records faster.
lov-search-chat
A local search tool for recalling relevant parts of earlier AI conversations from an indexed memory store. It returns matching sessions and identifiable excerpts from the original conversations.