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 ValorVie/custom-skills --skill work-log-claudegit clone --depth 1 https://github.com/ValorVie/custom-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/valorvie/custom-skills/work-log-claude)<a href="https://agentmods.dev/skills/valorvie/custom-skills/work-log-claude"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/work-log-claude/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/valorvie/custom-skills/work-log-claude"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/work-log-claude.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 | $0.00105 | $0.01993 |
| Opus 5.5 | $0.00042 | $0.00797 |
| Sonnet 5.5 | $0.00021 | $0.00399 |
| Haiku 4.5 | $0.00011 | $0.00199 |
Grade A, and why
work-log-claude 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 6d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Log Claude
只讀 Claude Code 的工作階段紀錄，產出與 work-log-codex 相同格式的工作日誌。
Claude 讀取器、解析、git 證據與 formatter 全部沿用 .agents/skills/work-log-codex；本 skill
只關掉 Codex 來源，所以兩者的報告結構、摘要規則與 prompt 完全一致。
資料來源
- 讀：
<claude-home>/projects/<cwd-slug>/<session>.jsonl（主工作階段）與<claude-home>/projects/<cwd-slug>/<session>/subagents/*.jsonl（subagent，子代理）。 - 只取
user／assistant紀錄。使用者提示只算真正輸入的文字；tool_result（工具回傳）、<command-name>之類的系統包裝與isMeta紀錄不當成提示。 - 專案＝該工作階段第一筆
cwd（啟動目錄），中途cd不會把工作階段拆到別的專案。 - 排除：
entrypoint為sdk-*的工作階段（記憶外掛之類的輔助工作階段）， 以及*observer-sessions目錄。 - 不讀：
~/.claude/transcripts/、history.jsonl、sessions/*.tmp。這些是舊版或其他工具 的格式，不是目前 Claude Code 的工作階段紀錄。 - 不讀任何 Codex 資料。
<claude-home> 預設是執行者的 ~/.claude，傳入時用絕對路徑。這個目錄通常只有本人讀得到，
其他帳號執行時會讀不到工作階段。
流程
與 work-log-codex 相同：有界 parser → 逐專案摘要 → 最終整合 → formatter。
下列命令都在 repo 根目錄執行。暫存目錄 WL_TMP
用本 session 的 scratchpad 目錄；沒有時先 mktemp -d 建立，之後每個命令寫出絕對路徑
（Bash 呼叫之間不保留 shell 變數）。
1. 解析時間範圍
today、yesterday、this-week、this-month、YYYY-MM-DD、YYYY-MM-DD YYYY-MM-DD。
可選 --project <name> 只看單一專案。
2. 執行 parser
stderr 顯示進度，stdout 只輸出 JSON。一次只跑一個 parser，多週一起跑再分週整理。
uv run --python 3.14 python .claude/skills/work-log-claude/scripts/work_log_claude.py parse \
TIME_RANGE [END_DATE] \
--timezone "Asia/Taipei" \
[--project "PROJECT"] \
--claude-home <absolute-claude-home> \
--emit-project-dir "$WL_TMP/wl_projects" \
> "$WL_TMP/wl_report.json"
3. 逐專案摘要
不要把整份 wl_report.json 讀進上下文。依序讀：
$WL_TMP/wl_projects/manifest.json- 每個專案 bundle JSON
.agents/skills/work-log-codex/prompts/project_summary.md
每個專案整理 2 至 5 個任務，格式與規則照 project_summary.md：
- **一行重點：** <一句可獨立閱讀的工作重點>
- **重點脈絡：** <300 字以內，說明起因、處理、結果與證據邊界>
- **來源：** <正式文件路徑及／或 repo@commit>
git_commits是完成項目的主證據；session_summaries補未提交、研究、規劃中的工作。- 沒有 commit 或正式文件時標成研究／規劃，來源寫「工作階段摘要（無 Git commit）」。
- 不要把原始工作階段 JSONL 當成正式完成證據。
git_commits是該 repo 在期間內的全部提交，可能包含 Codex 或人工做的提交。只把能對到 Claude 工作階段內容的提交寫進任務；其餘不要算成 Claude 的交付。
What ships with it
2 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.
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.
- 6d ago First seen · 131 lines · 105 tokens per session scan A aa0e8de0169a
work-log-claude is a skill published in the GitHub repository ValorVie/custom-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 1,993 once invoked, about $0.0004 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 2026-10-11.
Other skills, from other repositories
create-stories
Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria. Reads the control manifest. After /create-epics.
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
team-qa
Orchestrate the QA team through a full testing cycle — qa-lead strategy and test plan, qa-tester case writing, execution, sign-off.
create-epics
Turn GDDs plus architecture into epics — one per architectural module, with untraced requirements. Then /create-stories [epic-slug].
launch-checklist
Launch readiness across every department: code, content, store, marketing, community, infrastructure, legal, go/no-go sign-offs.
release-checklist
Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.