SkillAgentSearch skills...

read-claude-code-history

Reads, searches and exports local Claude Code and Kimi CLI history without resuming work: timelines, verbatim user input, keyword or fuzzy recall, file recovery from transcripts, and which session ran a given command in a known time window

Install / Use

npx skills add daymade/claude-code-skills --skill read-claude-code-history

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

93/100

Category

Marketing

Supported Platforms

Claude Code
OpenAI Codex

Tags

Our assessment of read-claude-code-history

read-claude-code-history scores 93/100 on our quality scale, 146th of 642 Marketing skills we index (top 23%).

Its SKILL.md is 21 KB long, well organised into 18 sections with 6 code examples: a thorough specification that gives an agent plenty to work with.

With 1,426 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so read-claude-code-history is actively maintained.
  • Our last check on 2026-10-26 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

read-claude-code-history compared with similar skills

All 4 of these similar skills score higher than read-claude-code-history; compare them before choosing.

SkillScoreStarsUpdatedFormat
read-claude-code-history (this skill)by daymade931.4k53d agoSKILL.md
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md
designby nextlevelbuilder100149.0k6d agoSKILL.md

Frequently asked questions

How do I install read-claude-code-history?
Run npx skills add daymade/claude-code-skills --skill read-claude-code-history. The install tabs above show the steps for each supported agent.
Which AI agents does read-claude-code-history work with?
It is written for Claude Code and OpenAI Codex, as a SKILL.md file. Other agents that read the same format can often use it too.
Is read-claude-code-history safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is read-claude-code-history still maintained?
The repository was last updated about 2 months ago, so read-claude-code-history is actively maintained.

name: read-claude-code-history description: >- Reads, searches and exports local Claude Code and Kimi CLI history without resuming work: timelines, verbatim user input, keyword or fuzzy recall, file recovery from transcripts. Use when the user asks what was said, wants a session ID or original context, or needs proof of what a session contained. Not for Codex (use read-codex-history); with no platform or several named, start at local-conversation-history. argument-hint: "[session-id | keywords | workspace-path]"

Read Claude Code History

Read Claude Code evidence only. Do not resume the old process, edit its project, or turn a read request into a continuation task. When the user later asks to act, hand the verified evidence to daymade-claude-code:continue-claude-code-work.

Route by the requested result

| User wants | Use | |---|---| | Recent Claude Code sessions, titles, dates, or IDs | Indexed metadata only; the bundled list_local_history.py currently reads all candidate bodies before date/limit filtering, so do not use it for a broad inventory | | One known Session reconstructed as a chronological evidence briefing | scripts/read_claude_session.py --session <ID> | | The exact command behind a hook audit row that records a Session ID and a command SHA-256 instead of the text | scripts/read_claude_session.py --session <ID> --find-command-sha256 <HEX>; see Command behind a hook audit row below | | Every Agent/Task tool_use in one Session, quoted verbatim (e.g. the exact prompt handed to an independent reviewer agent) | scripts/read_claude_session.py --session <ID> --agent-prompts (optionally --agent-description-prefix TEXT); a prompt dispatched twice is listed twice | | Which session launched a program in a known time window, across sessions | scripts/analyze_sessions.py tool-calls --from <ISO> --to <ISO> --pattern <REGEX> [--tool NAME]; candidates are selected by filesystem metadata before any body is read, then grouped by session; Codex rollouts are out of scope and the gap is stated in the output | | The user's recent words, including human queued prompts | scripts/extract_user_messages.py | | A conversation or quote by keyword | scripts/history_index.py recall --mode bm25, then the exact-session reader | | Prior work whose wording may have changed | scripts/history_index.py recall after checking index status | | A topic with no known Session ID | scripts/history_index.py status, then recall; state index coverage and freshness | | How identified sessions or a physically bounded project ended | Follow Inspect session endings in references/workflow_examples.md | | A deleted/overwritten file preserved in Claude file-history records | scripts/recover_content.py | | How often each Skill ran and who started it (user command, model after the user named it, model unprompted), e.g. to decide model-visible vs user-invocable-only | scripts/skill_usage_ledger.py index, then report (Claude and Codex together); see Skill usage ledger below | | Kimi CLI sessions | history_index.py recall --provider kimi, then read the named session's wire.jsonl; see Kimi CLI below | | Continue a verified Claude session | Stop reading and invoke daymade-claude-code:continue-claude-code-work |

找「我们之前做的那个 X」(产物类目标)的三个判据

按词搜不到时换这三个判据,别扩词硬搜:

  1. 时间约束是第一筛子。用户给了时间窗(「前两天」「本周」)→ 先按 mtime 筛文件系统(find <root> -newermt '<日期>' -name '*.html'),候选面缩到几十条再按形态排。全库关键词搜索应该在时间筛之后,不是之前。
  2. session scratchpad 必须在搜索面内(/private/tmp/claude-$(id -u)/**/scratchpad/,macOS 单用户通常是 claude-501)。Claude session 的默认产物落点在那,不在 workspace——「我们之前写的 X」有相当概率躺在 scratchpad。找产物类目标时显式包含它。
  3. 恢复出的版本 ≠ 最终版。从 session jsonl 恢复文件(取 Write 的 content)只拿到某次全量写,后续增量 Edit 不会自动合入——恢复产物可能只有真实文件的零头(实测:28KB 恢复片段 vs 2.45MB 完整版)。打开/渲染后觉得「不像目标」时,先怀疑「我拿到的不是完整版」(原路径文件还在不在、session 里还有没有后续 Edit),不要直接排除目标。

战例(2026-09-18):找「之前做的聚类网页」,十几轮全库关键词搜索无果;目标一直在 9-13 的 session scratchpad(favorites-ledger.html,2.45MB),恢复的 28KB 片段渲染成裸样式被误判排除,用户给出精确路径后才定位。

The requested output wins over the background story. If the user asks for a chronological table of their raw inputs, return that table; do not replace it with a topic analysis because their motivation mentions an incident.

Evidence surface and completeness

By default, discover every active Claude config home and every archive registered in ~/.claude/history-sources.json. De-duplicate physical copies by Session ID and content identity, and use record timestamps rather than file mtime. A result scoped to one explicit --home is a diagnostic slice, not a completeness claim.

Treat Claude's record labels as storage metadata, not authorship proof. A top-level type: user record can contain a command envelope, hook boilerplate, a whole pasted document, agent-voiced text, or a system placeholder. Human text typed while the assistant was busy can live in attachment.queued_command.prompt with origin.kind: human; do not lose those corrections by reading only user records.

Read references/session_file_format.md when interpreting schemas, authorship, sidechains, attachment records, compaction, or file-history snapshots. Read references/hybrid_history_recall.md before building or repairing the optional BM25/vector index. Read references/workflow_examples.md for indexed discovery, triage, and recovery examples. Read references/claude_session_format.md when you need the layout rather than the message schema — where sessions live on disk, how project paths are normalized into directory names, the sessions-index.json fields, and the compact_boundary markers that tell you a transcript was summarized rather than truncated.

Commands

Resolve every script relative to this SKILL.md; do not search the machine for a same-named helper or recreate a JSONL parser inline.

Indexed discovery

<skill-dir>/scripts/history_index.py status
<skill-dir>/scripts/history_index.py recall '<topic>' --provider claude --mode bm25

Expected output: candidate Session IDs and index coverage. This is topic discovery, not a complete recent-session inventory. If a complete list is needed, report that the current bundled inventory would scan raw bodies.

Exact Session evidence

<skill-dir>/scripts/read_claude_session.py --session <SESSION_ID>

# Add this only when the caller intentionally wants to restrict lookup to one workspace.
<skill-dir>/scripts/read_claude_session.py --session <SESSION_ID> --project <workspace>

Expected output: # Claude Code Session Evidence Briefing, session identity, compaction boundary, chronological user/assistant handoff, queued human prompts, end reason, unresolved calls, subagent state, files touched, memory, and current workspace state. The exact reader always parses every physical Session record, including records before compaction; --full only removes output character clipping. It checks active and registered-archive copies, accepts only identical or strict append-only supersets, and fails visibly on divergent copies, multiple Session identities, a missing record-level Session identity, malformed JSONL, or unreadable bytes. With an exact Session ID and no --project, it searches every project across the discovered active homes and registered archives; an explicit --project remains a strict scope. A filename alone never proves Session identity. Read Local runtime and working-directory evidence before interpreting task endings, local-command output, or cwd receipts.

Command behind a hook audit row

Hook audit logs often store sid=<SESSION_ID> cmd_sha256=<HEX> rather than the command text. Resolve a row to the tool call that produced it:

<skill-dir>/scripts/read_claude_session.py --session <SESSION_ID> --find-command-sha256 <HEX>

Expected output: a # Tool calls whose command has SHA-256 … heading, the number of transcript files and tool calls examined, the match count, and for each match the file and line, timestamp, record uuid, tool name and id, cwd, and the full command in a fence. Exit 0 means at least one match, 1 no match, 2 a malformed digest or missing --session. The digest is SHA-256 over tool_input.command as UTF-8. A hook event raised inside a subagent carries the parent Session ID, so the lookup also searches <SESSION_ID>/subagents/*.jsonl; a main-transcript-only search misses those calls. Unlike the briefing, the lookup skips and counts unparseable lines so it still works on a Session that is being written; a zero with skipped lines does not prove the call is absent.

Indexed content search

<skill-dir>/scripts/history_index.py status
<skill-dir>/scripts/history_index.py recall '<keyword>' \
  --mode bm25 --provider claude --exclude-session <CURRENT_ID>

Inspect the index's provider coverage and last indexed time. Open only matching Session IDs with the exact-session reader to verify original records. Indexed recall returns ranked prose candidates, not a census of thinking, tool results, attachments, or unindexed records. The raw analyze_sessions.py search entry is disabled for live stores: its date flags filter after reading the files.

Use --role user or --role assistant to narrow the stored role, and repeat --phrase '<literal text>' to require exact substrings. These filters constrain both BM25 and vector candidates; --terms constrains only the FTS leg. Returned record_key, source_kind, and human_authorship describe provenance, not an authenticated human speaker. Inspect the original record before saying “you said”. Codex tool results are outside this prose index; hand a selected Codex candidate to read-codex-history's original tool/record evidence route. Export original values without automatic content redaction. A result about a neighboring fact does not answer the requested proposition.

Human-input export

<skill-dir>/scripts/extract_user_messages.py \
  <persistent-output-base> --days 7 --group-by session

This produces Markdown and HTML. It separates storage pollution from human prose and recovers queued prompts. Preserve timestamps, duplicates, and Session boundaries; do not add a second thematic classification unless asked.

Deleted-content recovery

Recovery writes files, so keep it separate from ordinary reading. First run the recovery report against the exact Session file, review every proposed destination, then write only after the user asked to recover content. Never restore directly over the current project tree.

Skill usage ledger

Answers "which Skills do we actually use, and who starts them". It is an incremental index (~/.claude-history-index/skill-usage-v1.db): the first index parses every Claude and Codex session once, later runs re-parse only files whose size or mtime changed. Reports read the ledger, never raw history.

python3 scripts/skill_usage_ledger.py index            # --no-codex to skip Codex
python3 scripts/skill_usage_ledger.py report --override user-invocable-only
python3 scripts/skill_usage_ledger.py report <skill> [<skill> ...] --since 2026-06-01 --until 2026-09-24
python3 scripts/skill_usage_ledger.py status           # freshness + what is not covered

Columns: user_command (user typed /X, or Codex $X), model_named (the model invoked X and the latest human prompt contained X's name), model_auto (the model invoked X unprompted), last_model_use, blocked (Claude refused a model call because X is not model-invocable — the model reached for it and could not use it; not counted as use), and the Skill's current skillOverrides value. --override STATE also lists Skills in that state with zero recorded use. Rows group by bare name, which is what skillOverrides keys on; identities lists the qua

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars1.4k
CategoryMarketing
Updated1mo ago
Forks219

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions
read-claude-code-history — Claude Code Skill: Install & Safety Check | SkillAgent