Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
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 daymade/claude-code-skills --skill read-claude-code-historygit clone --depth 1 https://github.com/daymade/claude-code-skillsWrote 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/daymade/claude-code-skills/read-claude-code-history)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/read-claude-code-history"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/read-claude-code-history/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/daymade/claude-code-skills/read-claude-code-history"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/read-claude-code-history.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 71 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00132 | $0.06545 |
| Opus 5.5 | $0.00053 | $0.02618 |
| Sonnet 5.5 | $0.00026 | $0.01309 |
| Haiku 4.5 | $0.00013 | $0.00654 |
Grade A, and why
read-claude-code-history 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 8d 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 — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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> |
| Original tool input and paired result from one exact Session, selected by tool name, literal text, ordinal or time | scripts/read_claude_session.py --session <ID> --tool-evidence --contains '<literal>'; see Original tool call/result evidence below |
| 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 |
| When hook runs happened across sessions — outcome, duration, exit code per run (e.g. "why was session startup slow", "did this guard fire today") | scripts/analyze_sessions.py hook-events --from <ISO> --to <ISO> [--pattern <REGEX>] [--event NAME]; same candidate-first narrowing as tool-calls; forked-session copies of a run collapse to one; 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 |
| The latest conversation about a topic, including a newer continuation | Use recall to locate relevant project(s); for Codex, continue with read-codex-history's Latest topic across continuations route instead of treating relevance top-K as latest. Claude/Kimi have no indexed recent-session inventory here, so keep unverified continuation coverage unknown |
| 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 |
What ships with it
49 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.
- .INTEGRATION_SUMMARY.md 6.8 KB
- evals/evals.json 2.6 KB
- references/cc-behavior-claims.json 7.8 KB
- references/claude_session_format.md 8.6 KB
- references/hybrid_history_recall.md 26 KB
- references/large-session-briefing.md 5.9 KB
- references/legacy_cross_provider_workflow.md 29 KB
- references/session_file_format.md 33 KB
- references/workflow_examples.md 7.4 KB
- scripts/_core/__init__.py 1.3 KB runs code
- scripts/_core/claude.py 5.6 KB runs code
- scripts/_core/codex.py 12 KB runs code
- scripts/_core/homes.py 4.0 KB runs code
- scripts/_core/kimi.py 15 KB runs code
- scripts/_core/model.py 2.0 KB runs code
- scripts/_core/native_output.py 2.1 KB runs code
- scripts/_core/parse.py 6.2 KB runs code
- scripts/_core/sources.py 13 KB runs code
- scripts/_core/text.py 35 KB runs code
- scripts/analyze_sessions.py 152 KB runs code
- scripts/extract_user_messages.py 25 KB runs code
- scripts/history_index.py 136 KB runs code
- scripts/list_local_history.py 35 KB runs code
- scripts/read_claude_session.py 103 KB runs code
- scripts/recover_content.py 49 KB runs code
- scripts/skill_usage_ledger.py 33 KB runs code
- scripts/surface_version.py 1.1 KB runs code
- scripts/verify_cc_claims.py 14 KB runs code
- tests/fixtures/real-derived/askuserquestion-answer.jsonl 1.2 KB
- tests/fixtures/real-derived/plan-binding-attachment.jsonl 615 B
- tests/fixtures/real-derived/read-numbered-result.jsonl 826 B
- tests/fixtures/real-derived/thinking-only-assistant.jsonl 586 B
- tests/fixtures/real-derived/tool-result-before-use.jsonl 1.0 KB
- tests/test_analyze_sessions.py 69 KB runs code
- tests/test_cc_behavior_claims.py 2.6 KB runs code
- tests/test_core_text.py 14 KB runs code
- tests/test_extract_user_messages.py 12 KB runs code
- tests/test_history_index.py 139 KB runs code
- tests/test_hook_events.py 9.8 KB runs code
- tests/test_kimi_search.py 28 KB runs code
- tests/test_list_local_history.py 58 KB runs code
- tests/test_native_output.py 2.9 KB runs code
- tests/test_read_claude_session.py 74 KB runs code
- tests/test_recover_content.py 25 KB runs code
- tests/test_skill_usage_ledger.py 15 KB runs code
- tests/test_snapshot_freshness.py 12 KB runs code
- tests/test_surface_version.py 2.1 KB runs code
- tests/test_tool_calls.py 11 KB runs code
- tests/test_tool_evidence.py 19 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.
- 8d ago Changed · +6 lines 83ccb5ed17cd
- 12d ago Changed · +16 lines 09f54b5491aa
- 16d ago Changed · +6 lines 39ba43caf766
- 23d ago Changed · +59 lines bb4d32fd536e
- 1mo ago Changed · +3 lines · +38 tokens per session 42dd77c1c6f8
- 1mo ago Changed · +10 lines 956b0a2dc1b2
- 1mo ago Changed · +2 lines ab4a91712bf3
- 1mo ago Changed · +2 lines caa3d30de37b
- 1mo ago Changed · +21 lines 596f389e02c2
- 1mo ago First seen · 323 lines · 94 tokens per session scan A 10eb87d25a82
read-claude-code-history is a skill published in the GitHub repository daymade/claude-code-skills (1,516 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 6,545 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
read-claude-code-history compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| read-claude-code-historydaymade/claude-code-skills | Skill | 1.5k | yesterday | MIT | A | 132 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |